|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/44217
|
-66.47% |
95831.184 |
32130.922 |
22604.562 |
-64.66% |
22604.562 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/5001
|
-62.52% |
9835.077 |
3685.923 |
2109.224 |
-59.55% |
2109.224 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DISC_ORD_LAMBDA/44217
|
-58.34% |
14942.907 |
6225.385 |
3366.611 |
-55.70% |
3366.611 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint32_t_
|
-52.18% |
35281.317 |
16870.393 |
472.676 |
-52.23% |
472.676 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint16_t_
|
-50.84% |
35690.629 |
17545.855 |
243.657 |
-50.82% |
243.657 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint8_t_
|
-49.72% |
37106.169 |
18658.083 |
46.793 |
-49.66% |
46.793 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/miniGMG/miniGMG
Profile
|
-46.03% |
8.577 |
4.629 |
0.102 |
-49.63% |
0.102 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint64_t_
|
-43.93% |
18637.529 |
10450.801 |
44.165 |
-44.04% |
44.165 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/44217
|
-42.00% |
23218.082 |
13466.394 |
293.213 |
-42.20% |
293.213 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/44217
|
-41.89% |
23167.222 |
13461.436 |
344.032 |
-41.73% |
344.032 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/5001
|
-41.52% |
2586.259 |
1512.415 |
10.438 |
-41.26% |
10.438 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint64_t_
|
-41.39% |
17923.703 |
10505.407 |
11.488 |
-40.98% |
11.488 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/5001
|
-40.95% |
2567.064 |
1515.927 |
35.524 |
-39.59% |
35.524 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint32_t_
|
-40.76% |
38169.565 |
22612.009 |
31.030 |
-40.74% |
31.030 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint64_t_
|
-39.01% |
22587.852 |
13776.022 |
211.491 |
-39.38% |
211.491 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/32
|
-36.71% |
1396.288 |
883.760 |
0.033 |
-36.70% |
0.033 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/64
|
-36.67% |
6182.119 |
3915.304 |
2.658 |
-36.67% |
2.658 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/16
|
-36.63% |
279.496 |
177.104 |
0.013 |
-36.63% |
0.013 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/256
|
-36.25% |
107147.476 |
68303.900 |
52.994 |
-36.26% |
52.994 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/128
|
-36.10% |
26269.690 |
16785.543 |
3.463 |
-36.11% |
3.463 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint8_t_
|
-34.51% |
30179.874 |
19765.493 |
37.953 |
-34.36% |
37.953 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint16_t_
|
-33.82% |
28930.163 |
19147.027 |
6.019 |
-33.86% |
6.019 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_DIFF_RAW/44217
|
-30.83% |
146.623 |
101.426 |
0.798 |
-28.82% |
0.798 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_DIFF_LAMBDA/44217
|
-30.17% |
145.079 |
101.316 |
0.914 |
-30.04% |
0.914 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint16_t_
|
-28.69% |
25916.275 |
18480.683 |
55.765 |
-28.64% |
55.765 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/44217
|
-28.47% |
71246.500 |
50960.327 |
2739.869 |
-39.80% |
2739.869 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint8_t_
|
-27.88% |
13467.045 |
9712.814 |
19.244 |
-27.89% |
19.244 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/44217
|
-27.35% |
11907.966 |
8651.472 |
37.068 |
-22.87% |
37.068 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC128
|
-27.15% |
1298.119 |
945.742 |
5.115 |
-26.85% |
5.115 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC128
|
-27.03% |
558.406 |
407.458 |
0.031 |
-26.92% |
0.031 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/44217
|
-26.61% |
11772.169 |
8639.664 |
574.667 |
-21.19% |
574.667 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC32
|
-26.44% |
335.102 |
246.485 |
1.662 |
-26.19% |
1.662 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC64
|
-26.38% |
655.605 |
482.684 |
2.703 |
-26.15% |
2.703 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC16
|
-25.85% |
174.211 |
129.180 |
1.061 |
-25.67% |
1.061 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC64
|
-25.67% |
292.145 |
217.157 |
0.075 |
-25.59% |
0.075 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint8_t_
|
-24.79% |
27200.661 |
20458.302 |
33.104 |
-24.85% |
33.104 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC32
|
-23.19% |
158.885 |
122.046 |
0.042 |
-23.18% |
0.042 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC128
|
-23.12% |
604.044 |
464.379 |
0.057 |
-23.11% |
0.057 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC128
|
-23.12% |
604.039 |
464.396 |
0.008 |
-23.11% |
0.008 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/1024
|
-22.85% |
30116.951 |
23235.462 |
71.332 |
-22.93% |
71.332 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC64
|
-22.17% |
313.535 |
244.024 |
0.164 |
-22.16% |
0.164 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC64
|
-22.16% |
313.512 |
244.026 |
0.017 |
-22.16% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC127
|
-21.99% |
615.268 |
479.962 |
0.020 |
-21.98% |
0.020 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC127
|
-21.99% |
615.290 |
480.004 |
0.051 |
-21.98% |
0.051 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint64_t_
|
-21.63% |
13227.607 |
10365.916 |
2.631 |
-21.52% |
2.631 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint32_t_
|
-21.55% |
7106.243 |
5574.970 |
4.002 |
-21.49% |
4.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint32_t_
|
-21.46% |
6577.459 |
5166.157 |
3.708 |
-21.51% |
3.708 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC4
|
-21.43% |
17.521 |
13.766 |
0.001 |
-21.43% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_uint8_t_
|
-21.38% |
182352.473 |
143364.250 |
45.395 |
-21.38% |
45.395 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_SUM_LAMBDA/44217
|
-21.31% |
171.585 |
135.015 |
0.685 |
-19.19% |
0.685 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/171
|
-21.29% |
1.501 |
1.181 |
0.000 |
-21.28% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/5001
|
-21.22% |
7532.433 |
5933.682 |
171.151 |
-32.54% |
171.151 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/44217
|
-21.14% |
389.291 |
307.011 |
0.203 |
-21.19% |
0.203 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/5001
|
-20.81% |
45.160 |
35.761 |
0.173 |
-20.98% |
0.173 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC32
|
-20.46% |
168.338 |
133.898 |
0.010 |
-20.46% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC32
|
-20.45% |
168.324 |
133.902 |
0.009 |
-20.45% |
0.009 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_SUM_RAW/44217
|
-20.35% |
170.935 |
136.149 |
0.233 |
-18.15% |
0.233 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC63
|
-20.06% |
324.819 |
259.669 |
0.011 |
-20.05% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC63
|
-20.06% |
324.819 |
259.676 |
0.005 |
-20.05% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC128
|
-19.89% |
570.815 |
457.287 |
6.743 |
-19.86% |
6.743 |
|
SingleSource/Benchmarks/Adobe-C++/loop_unroll
Profile
|
-19.77% |
2.990 |
2.399 |
0.001 |
-22.79% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC127
|
-19.73% |
641.137 |
514.667 |
0.069 |
-19.65% |
0.069 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC128
|
-19.62% |
274.325 |
220.503 |
0.740 |
-19.74% |
0.740 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC127
|
-19.43% |
275.063 |
221.623 |
1.305 |
-19.54% |
1.305 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC32
|
-19.38% |
161.442 |
130.150 |
1.630 |
-19.36% |
1.630 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC16
|
-19.21% |
92.288 |
74.555 |
0.017 |
-19.21% |
0.017 |
|
MultiSource/Benchmarks/MiBench/automotive-bitcount/automotive-bitcount
Profile
|
-19.20% |
0.125 |
0.101 |
0.001 |
-18.48% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint8_t_
|
-19.16% |
13892.321 |
11230.853 |
71.130 |
-19.21% |
71.130 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint8_t_
|
-19.03% |
3815.444 |
3089.489 |
0.041 |
-19.08% |
0.041 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC8
|
-18.92% |
23.152 |
18.771 |
0.178 |
-18.93% |
0.178 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/2
|
-18.81% |
8.757 |
7.111 |
0.000 |
-18.80% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/2
|
-18.79% |
8.757 |
7.111 |
0.001 |
-18.80% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, None>
|
-18.75% |
20512.559 |
16666.357 |
1.292 |
-18.75% |
1.292 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/5001
|
-18.70% |
1144.966 |
930.838 |
26.760 |
-13.68% |
26.760 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint16_t_
|
-18.65% |
13803.930 |
11229.559 |
8.018 |
-18.67% |
8.018 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint32_t_
|
-18.58% |
27082.695 |
22049.467 |
32.152 |
-18.49% |
32.152 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC64
|
-18.55% |
297.898 |
242.628 |
1.684 |
-18.50% |
1.684 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint64_t_
|
-18.41% |
13357.200 |
10898.561 |
13.595 |
-16.58% |
13.595 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC16
|
-18.23% |
93.238 |
76.244 |
0.488 |
-18.13% |
0.488 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Last>
|
-18.18% |
14104.183 |
11540.724 |
0.651 |
-18.18% |
0.651 |
|
MultiSource/Benchmarks/Trimaran/enc-pc1/enc-pc1
Profile
|
-18.15% |
1.105 |
0.904 |
0.000 |
-18.11% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC64
|
-18.12% |
148.303 |
121.431 |
3.318 |
-18.30% |
3.318 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_uint8_t_
|
-17.88% |
746296.594 |
612854.255 |
62.198 |
-17.82% |
62.198 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC16
|
-17.66% |
95.746 |
78.840 |
0.007 |
-17.65% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC16
|
-17.65% |
95.740 |
78.842 |
0.003 |
-17.65% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC8
|
-17.64% |
58.818 |
48.443 |
0.319 |
-17.56% |
0.319 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_1D_RAW/44217
|
-17.57% |
13396.689 |
11042.360 |
81.481 |
-18.38% |
81.481 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int32_t_
|
-17.54% |
740484.035 |
610639.203 |
1187.788 |
-17.50% |
1187.788 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC7
|
-17.35% |
28.021 |
23.159 |
0.040 |
-19.20% |
0.040 |
|
MultiSource/Benchmarks/MiBench/security-rijndael/security-rijndael
Profile
|
-17.16% |
0.335 |
0.277 |
0.000 |
-17.14% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC31
|
-16.73% |
179.596 |
149.548 |
0.003 |
-16.72% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC31
|
-16.73% |
179.586 |
149.541 |
0.008 |
-16.73% |
0.008 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/0
|
-16.31% |
1268.602 |
1061.741 |
2.020 |
-16.24% |
2.020 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/0
|
-16.22% |
1267.625 |
1061.966 |
1.765 |
-16.06% |
1.765 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/1
|
-16.19% |
260.208 |
218.092 |
0.081 |
-16.16% |
0.081 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_1D_RAW/171
|
-16.10% |
0.443 |
0.372 |
0.000 |
-15.84% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/1
|
-16.06% |
259.966 |
218.223 |
0.007 |
-16.12% |
0.007 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_1D_LAMBDA/171
|
-15.81% |
0.441 |
0.372 |
0.000 |
-15.88% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC8
|
-15.78% |
23.778 |
20.024 |
0.002 |
-15.79% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint32_t_
|
-15.64% |
7462.029 |
6295.133 |
1.115 |
-15.64% |
1.115 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC127
|
-15.51% |
605.920 |
511.955 |
1.538 |
-15.49% |
1.538 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_no_runtime_checks_needed<16, int>
|
-15.38% |
24.401 |
20.648 |
0.001 |
-15.39% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint8_t_
|
-15.23% |
21966.959 |
18621.790 |
39.278 |
-15.54% |
39.278 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint8_t_
|
-15.16% |
10636.219 |
9024.249 |
21.876 |
-14.83% |
21.876 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC16
|
-15.08% |
33.162 |
28.159 |
0.588 |
-15.09% |
0.588 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/5001
|
-14.84% |
1101.540 |
938.057 |
24.685 |
-15.15% |
24.685 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_PRESSURE_CALC_RAW/5001
|
-14.68% |
45.936 |
39.193 |
1.719 |
-12.12% |
1.719 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC128
|
-14.58% |
1103.530 |
942.646 |
0.217 |
-14.56% |
0.217 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC64
|
-14.55% |
562.571 |
480.706 |
0.799 |
-14.51% |
0.799 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC15
|
-14.49% |
44.639 |
38.169 |
0.001 |
-14.09% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC127
|
-14.42% |
1095.451 |
937.458 |
0.041 |
-14.41% |
0.041 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC32
|
-14.38% |
292.205 |
250.181 |
0.939 |
-14.32% |
0.939 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint16_t_
|
-14.27% |
19067.892 |
16346.554 |
423.941 |
-13.89% |
423.941 |
|
External/SPEC/CFP2017rate/508.namd_r/508.namd_r
Profile
|
-14.19% |
224.637 |
192.772 |
0.850 |
-13.78% |
0.850 |
|
SingleSource/Benchmarks/Misc/salsa20
Profile
|
-14.14% |
15.387 |
13.211 |
0.001 |
-14.12% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC63
|
-14.11% |
554.504 |
476.275 |
0.248 |
-14.14% |
0.248 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint16_t_
|
-14.05% |
12796.318 |
10999.049 |
21.477 |
-14.32% |
21.477 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint16_t_
|
-14.00% |
3756.761 |
3230.899 |
2.198 |
-13.99% |
2.198 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_autovec_int64_t_
|
-13.95% |
790544.538 |
680302.723 |
1564.599 |
-14.06% |
1564.599 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC2
|
-13.87% |
51.943 |
44.738 |
0.004 |
-13.86% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int64_t_
|
-13.87% |
790333.848 |
680735.014 |
1181.062 |
-13.62% |
1181.062 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC3
|
-13.86% |
51.938 |
44.738 |
0.001 |
-13.86% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC4
|
-13.86% |
51.936 |
44.737 |
0.002 |
-13.86% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC8
|
-13.86% |
51.938 |
44.739 |
0.003 |
-13.86% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC7
|
-13.86% |
51.938 |
44.739 |
0.007 |
-13.85% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC1
|
-13.86% |
51.937 |
44.739 |
0.001 |
-13.85% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC8
|
-13.69% |
59.447 |
51.308 |
0.003 |
-13.70% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC8
|
-13.69% |
59.446 |
51.310 |
0.003 |
-13.69% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC31
|
-13.54% |
284.081 |
245.604 |
0.439 |
-13.55% |
0.439 |
|
MultiSource/Benchmarks/TSVC/CrossingThresholds-flt/CrossingThresholds-flt
Profile
|
-13.41% |
10.713 |
9.276 |
0.082 |
-13.81% |
0.082 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC63
|
-13.37% |
374.434 |
324.372 |
0.049 |
-13.37% |
0.049 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint8_t_
|
-13.37% |
11027.330 |
9553.294 |
45.139 |
-14.16% |
45.139 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/1024
|
-13.26% |
7418.391 |
6434.585 |
151.040 |
-9.51% |
151.040 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC128
|
-13.08% |
81.348 |
70.707 |
0.002 |
-13.08% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint16_t_
|
-12.95% |
4542.182 |
3953.811 |
0.206 |
-12.95% |
0.206 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC63
|
-12.95% |
332.947 |
289.840 |
0.096 |
-12.91% |
0.096 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC16
|
-12.94% |
157.060 |
136.744 |
0.135 |
-12.88% |
0.135 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-matrix
Profile
|
-12.73% |
2.509 |
2.190 |
0.000 |
-12.69% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC31
|
-12.58% |
86.256 |
75.402 |
0.472 |
-12.44% |
0.472 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint8_t_
|
-12.40% |
4743.547 |
4155.178 |
0.122 |
-12.39% |
0.122 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC15
|
-12.17% |
51.939 |
45.619 |
0.169 |
-12.17% |
0.169 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC16
|
-12.04% |
51.939 |
45.684 |
0.144 |
-12.05% |
0.144 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC15
|
-12.03% |
148.937 |
131.026 |
0.180 |
-11.95% |
0.180 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, None>
|
-12.00% |
16024.062 |
14101.611 |
0.868 |
-11.99% |
0.868 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC2
|
-11.77% |
21.276 |
18.772 |
0.001 |
-11.77% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC15
|
-11.70% |
107.000 |
94.480 |
0.008 |
-11.70% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC15
|
-11.70% |
107.000 |
94.481 |
0.004 |
-11.71% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC4
|
-11.32% |
113.720 |
100.845 |
1.304 |
-10.83% |
1.304 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC32
|
-11.24% |
85.703 |
76.071 |
0.115 |
-10.85% |
0.115 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC4
|
-11.12% |
22.526 |
20.022 |
0.001 |
-11.12% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC3
|
-11.12% |
22.527 |
20.023 |
0.000 |
-11.11% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC4
|
-11.11% |
22.526 |
20.024 |
0.002 |
-11.11% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/51
|
-11.10% |
123.904 |
110.155 |
0.127 |
19.08% |
0.127 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/44217
|
-10.97% |
8987.919 |
8001.891 |
82.692 |
-11.57% |
82.692 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/44217
|
-10.85% |
8946.271 |
7975.331 |
90.006 |
-4.35% |
90.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC63
|
-10.74% |
149.516 |
133.456 |
1.692 |
-10.98% |
1.692 |
|
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
|
-10.61% |
0.384 |
0.343 |
0.000 |
-6.33% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC8
|
-10.61% |
89.477 |
79.988 |
0.049 |
-10.53% |
0.049 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC4
|
-10.53% |
23.778 |
21.274 |
0.001 |
-10.53% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_1D_LAMBDA/5001
|
-10.47% |
16.850 |
15.085 |
0.663 |
-12.16% |
0.663 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC64
|
-10.47% |
53.814 |
48.180 |
0.002 |
-10.47% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/5001
|
-10.46% |
1017.188 |
910.758 |
4.211 |
-0.29% |
4.211 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/5001
|
-10.46% |
1019.922 |
913.227 |
2.605 |
0.94% |
2.605 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC16
|
-10.35% |
36.292 |
32.538 |
0.001 |
-10.35% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/16
|
-10.17% |
115.471 |
103.727 |
0.008 |
-10.17% |
0.008 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_PRESSURE_CALC_LAMBDA/5001
|
-10.13% |
45.890 |
41.241 |
0.811 |
-6.21% |
0.811 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint16_t_
|
-10.10% |
5848.721 |
5257.787 |
4.458 |
-10.13% |
4.458 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/64
|
-10.04% |
1913.909 |
1721.833 |
3.281 |
-10.01% |
3.281 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/32
|
-10.00% |
473.042 |
425.727 |
0.009 |
-10.00% |
0.009 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/256
|
-9.89% |
31444.142 |
28335.785 |
13.176 |
-9.90% |
13.176 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/128
|
-9.82% |
7916.622 |
7138.832 |
4.897 |
-9.83% |
4.897 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC127
|
-9.80% |
101.975 |
91.979 |
0.003 |
-9.72% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC8
|
-9.76% |
25.655 |
23.151 |
0.002 |
-9.77% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC8
|
-9.76% |
25.655 |
23.152 |
0.000 |
-9.76% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC31
|
-9.74% |
196.484 |
177.344 |
0.018 |
-9.74% |
0.018 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint64_t_
|
-9.72% |
16967.033 |
15317.307 |
136.381 |
-10.93% |
136.381 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC7
|
-9.62% |
32.539 |
29.409 |
0.001 |
-9.62% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int64_t_
|
-9.60% |
333406.443 |
301397.053 |
60.522 |
-9.57% |
60.522 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC7
|
-9.53% |
26.281 |
23.777 |
0.001 |
-9.53% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC7
|
-9.44% |
81.346 |
73.666 |
0.079 |
-9.40% |
0.079 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC7
|
-9.41% |
26.280 |
23.806 |
0.025 |
-9.42% |
0.025 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/1
|
-9.23% |
287.079 |
260.593 |
0.020 |
-9.24% |
0.020 |
|
MultiSource/Benchmarks/FreeBench/pifft/pifft
Profile
|
-9.22% |
0.360 |
0.327 |
0.001 |
-8.82% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint16_t_
|
-9.20% |
10637.416 |
9658.666 |
172.211 |
-10.05% |
172.211 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/1
|
-9.18% |
286.986 |
260.644 |
0.102 |
-9.18% |
0.102 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint32_t_
|
-9.12% |
18152.526 |
16496.867 |
210.133 |
-7.39% |
210.133 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC4
|
-9.10% |
41.302 |
37.545 |
0.000 |
-9.09% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC4
|
-9.10% |
41.298 |
37.542 |
0.003 |
-9.10% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC32
|
-9.01% |
53.184 |
48.392 |
0.003 |
-9.03% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC4
|
-9.00% |
55.697 |
50.683 |
0.002 |
-8.95% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC7
|
-8.88% |
28.156 |
25.656 |
0.002 |
-8.89% |
0.002 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<4, int>
|
-8.71% |
16.792 |
15.329 |
0.001 |
-8.25% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC2
|
-8.70% |
14.392 |
13.140 |
0.001 |
-8.70% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/2
|
-8.70% |
3.510 |
3.204 |
0.000 |
-8.70% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/2
|
-8.70% |
3.510 |
3.204 |
0.000 |
-8.70% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC8
|
-8.70% |
14.392 |
13.140 |
0.000 |
-8.70% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC16
|
-8.70% |
14.392 |
13.141 |
0.000 |
-8.69% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC3
|
-8.70% |
14.392 |
13.140 |
0.000 |
-8.70% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC8
|
-8.70% |
14.391 |
13.140 |
0.001 |
-8.70% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC3
|
-8.70% |
14.391 |
13.140 |
0.001 |
-8.71% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC16
|
-8.70% |
14.392 |
13.140 |
0.000 |
-8.70% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC4
|
-8.70% |
14.392 |
13.141 |
0.001 |
-8.70% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC1
|
-8.69% |
14.393 |
13.141 |
0.001 |
-8.70% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC7
|
-8.69% |
14.392 |
13.141 |
0.000 |
-8.69% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC1
|
-8.69% |
14.391 |
13.140 |
0.001 |
-8.70% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC15
|
-8.69% |
14.391 |
13.140 |
0.001 |
-8.70% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC15
|
-8.69% |
14.391 |
13.140 |
0.001 |
-8.70% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC4
|
-8.69% |
14.391 |
13.140 |
0.001 |
-8.70% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC7
|
-8.69% |
14.392 |
13.141 |
0.000 |
-8.69% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC2
|
-8.69% |
14.391 |
13.141 |
0.000 |
-8.69% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC8
|
-8.51% |
29.410 |
26.907 |
0.001 |
-8.52% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint8_t_
|
-8.51% |
6808.473 |
6229.333 |
21.275 |
-8.60% |
21.275 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/171
|
-8.43% |
88.831 |
81.339 |
0.901 |
-8.26% |
0.901 |
|
MultiSource/Benchmarks/McCat/12-IOtest/iotest
Profile
|
-8.28% |
1.828 |
1.676 |
0.030 |
-8.13% |
0.030 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/28
|
-8.25% |
82.589 |
75.776 |
0.250 |
12.11% |
0.250 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC64
|
-8.05% |
93.228 |
85.726 |
0.005 |
-8.06% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC16
|
-8.00% |
31.286 |
28.784 |
0.009 |
-8.01% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint8_t_To_uint32_t_
|
-7.97% |
12786.747 |
11767.386 |
7.193 |
-7.91% |
7.193 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC16
|
-7.85% |
31.914 |
29.409 |
0.004 |
-7.84% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC16
|
-7.85% |
31.912 |
29.409 |
0.002 |
-7.85% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC32
|
-7.81% |
40.044 |
36.918 |
0.003 |
-7.82% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC15
|
-7.69% |
32.537 |
30.035 |
0.002 |
-7.69% |
0.002 |
|
MultiSource/Benchmarks/VersaBench/beamformer/beamformer
Profile
|
-7.63% |
5.201 |
4.804 |
0.001 |
-7.63% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint64_t_
|
-7.62% |
20274.633 |
18730.119 |
108.898 |
-7.01% |
108.898 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/0
|
-7.61% |
1795.912 |
1659.235 |
4.155 |
-7.86% |
4.155 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC15
|
-7.61% |
54.437 |
50.295 |
0.006 |
-7.62% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC31
|
-7.56% |
74.465 |
68.836 |
0.003 |
-7.56% |
0.003 |
|
MultiSource/Benchmarks/Trimaran/enc-md5/enc-md5
Profile
|
-7.54% |
3.507 |
3.243 |
0.000 |
-7.50% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/171
|
-7.49% |
88.413 |
81.791 |
0.203 |
-7.71% |
0.203 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_no_runtime_checks_needed<16, int>
|
-7.40% |
16.893 |
15.643 |
0.001 |
-7.41% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint64_t_
|
-7.37% |
25077.650 |
23229.290 |
29.932 |
-7.03% |
29.932 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/0
|
-7.30% |
1792.479 |
1661.680 |
1.182 |
-7.27% |
1.182 |
|
MultiSource/Applications/lambda-0.1.3/lambda
Profile
|
-7.29% |
15.880 |
14.722 |
0.010 |
-7.23% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC128
|
-7.27% |
68.828 |
63.822 |
0.005 |
-7.24% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC128
|
-7.23% |
173.344 |
160.807 |
0.006 |
-7.22% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/127
|
-7.20% |
138.908 |
128.905 |
0.008 |
-7.20% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC127
|
-7.19% |
68.770 |
63.824 |
0.001 |
-6.54% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/171
|
-7.18% |
1.497 |
1.390 |
0.000 |
-7.15% |
0.000 |
|
MultiSource/Benchmarks/TSVC/NodeSplitting-dbl/NodeSplitting-dbl
Profile
|
-7.06% |
27.539 |
25.593 |
0.191 |
-3.11% |
0.191 |
|
SingleSource/Benchmarks/Misc/pi
Profile
|
-7.03% |
1.782 |
1.657 |
0.000 |
-7.02% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC63
|
-6.97% |
114.510 |
106.528 |
0.015 |
-6.97% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC15
|
-6.95% |
45.053 |
41.923 |
0.001 |
-6.94% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_BAND_LIN_EQ_RAW/5001
|
-6.82% |
21.433 |
19.971 |
0.139 |
-3.16% |
0.139 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC63
|
-6.70% |
74.439 |
69.453 |
0.003 |
-6.43% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/171
|
-6.70% |
11.904 |
11.107 |
0.051 |
-6.92% |
0.051 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC127
|
-6.66% |
194.618 |
181.656 |
0.191 |
-6.66% |
0.191 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC2
|
-6.57% |
38.175 |
35.668 |
0.003 |
-6.56% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC8
|
-6.54% |
26.780 |
25.029 |
0.001 |
-7.00% |
0.001 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_runtime_checks_pass<16, int>
|
-6.52% |
28.784 |
26.906 |
0.001 |
-6.52% |
0.001 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_runtime_checks_fail<16, int>
|
-6.52% |
28.783 |
26.907 |
0.001 |
-6.52% |
0.001 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/miniFE/miniFE
Profile
|
-6.52% |
15.822 |
14.790 |
0.070 |
-7.38% |
0.070 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/5001
|
-6.49% |
45.362 |
42.420 |
0.081 |
-6.44% |
0.081 |
|
SingleSource/Benchmarks/Misc/flops-6
Profile
|
-6.48% |
1.311 |
1.226 |
0.000 |
-6.55% |
0.000 |
|
SingleSource/Benchmarks/Misc/oourafft
Profile
|
-6.48% |
15.451 |
14.450 |
0.039 |
-4.26% |
0.039 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_PRESSURE_CALC_LAMBDA/44217
|
-6.45% |
508.814 |
476.001 |
2.953 |
-4.52% |
2.953 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int32_t_
|
-6.37% |
180888.207 |
169371.564 |
508.952 |
-6.49% |
508.952 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC15
|
-6.35% |
39.419 |
36.917 |
0.001 |
-6.36% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/127
|
-6.31% |
138.912 |
130.150 |
0.004 |
-6.31% |
0.004 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_MAT_X_MAT_RAW/5001
|
-6.29% |
847204.038 |
793877.787 |
19455.698 |
-4.98% |
19455.698 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_PRESSURE_CALC_RAW/44217
|
-6.29% |
500.766 |
469.283 |
6.303 |
-6.55% |
6.303 |
|
SingleSource/Benchmarks/Misc-C++/Large/sphereflake
Profile
|
-6.21% |
20.017 |
18.773 |
0.001 |
-6.15% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC16
|
-6.15% |
40.673 |
38.170 |
0.001 |
-6.16% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/171
|
-6.14% |
11.838 |
11.111 |
0.036 |
-7.30% |
0.036 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC32
|
-6.13% |
61.323 |
57.565 |
0.003 |
-6.13% |
0.003 |
|
External/SPEC/CFP2017rate/538.imagick_r/538.imagick_r
Profile
|
-6.00% |
291.904 |
274.381 |
0.334 |
-6.06% |
0.334 |
|
SingleSource/Benchmarks/Misc/perlin
Profile
|
-5.98% |
6.599 |
6.205 |
0.000 |
-5.97% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC15
|
-5.93% |
128.271 |
120.669 |
0.194 |
-5.92% |
0.194 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/65
|
-5.91% |
95.111 |
89.491 |
0.003 |
-5.91% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/127
|
-5.89% |
138.297 |
130.147 |
0.005 |
-5.89% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint64_t_
|
-5.78% |
21434.765 |
20196.369 |
55.839 |
-5.85% |
55.839 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC63
|
-5.72% |
43.805 |
41.297 |
0.001 |
-4.61% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC16
|
-5.66% |
33.162 |
31.287 |
0.001 |
-5.66% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC32
|
-5.64% |
44.428 |
41.922 |
0.002 |
-5.64% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC32
|
-5.64% |
44.428 |
41.922 |
0.002 |
-5.64% |
0.002 |
|
MultiSource/Benchmarks/SciMark2-C/scimark2
Profile
|
-5.63% |
107.740 |
101.677 |
0.062 |
-5.54% |
0.062 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC31
|
-5.59% |
45.067 |
42.548 |
0.001 |
-5.58% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC31
|
-5.55% |
45.050 |
42.548 |
0.001 |
-5.56% |
0.001 |
|
MultiSource/Benchmarks/Rodinia/hotspot/hotspot
Profile
|
-5.48% |
2.035 |
1.924 |
0.005 |
-5.52% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint8_t_To_uint16_t_
|
-5.40% |
3626.006 |
3430.222 |
8.106 |
-5.59% |
8.106 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/999
|
-5.40% |
696.535 |
658.927 |
0.048 |
-5.40% |
0.048 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/44217
|
-5.38% |
389.183 |
368.247 |
0.550 |
-5.48% |
0.550 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC64
|
-5.36% |
43.637 |
41.297 |
0.002 |
-4.35% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/5001
|
-5.31% |
21.449 |
20.310 |
0.084 |
-2.35% |
0.084 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC7
|
-5.31% |
70.704 |
66.951 |
0.016 |
-5.32% |
0.016 |
|
SingleSource/Benchmarks/Polybench/stencils/jacobi-2d/jacobi-2d
Profile
|
-5.31% |
32.075 |
30.373 |
0.148 |
-5.74% |
0.148 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC7
|
-5.30% |
70.706 |
66.960 |
0.004 |
-5.32% |
0.004 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/171
|
-5.28% |
13.517 |
12.803 |
0.073 |
-5.44% |
0.073 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC1
|
-5.26% |
11.889 |
11.263 |
0.000 |
-5.27% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC3
|
-5.26% |
47.555 |
45.053 |
0.002 |
-5.27% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/999
|
-5.22% |
1364.971 |
1293.749 |
0.081 |
-5.22% |
0.081 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/171
|
-5.02% |
13.470 |
12.795 |
0.043 |
-5.21% |
0.043 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC31
|
-4.99% |
241.221 |
229.176 |
0.135 |
-5.00% |
0.135 |
|
SingleSource/Benchmarks/Stanford/Puzzle
Profile
|
-4.83% |
0.241 |
0.230 |
0.004 |
-4.81% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC15
|
-4.81% |
32.539 |
30.973 |
0.003 |
-4.81% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/256
|
-4.81% |
364.172 |
346.660 |
0.005 |
-4.81% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint64_t_
|
-4.75% |
23513.592 |
22397.192 |
11.307 |
-4.63% |
11.307 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_cond_load_novec_int32_t_
|
-4.72% |
420378.068 |
400532.325 |
729.620 |
-2.48% |
729.620 |
|
SingleSource/Benchmarks/Misc/revertBits
Profile
|
-4.69% |
0.641 |
0.611 |
0.000 |
-4.67% |
0.000 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<16, int>
|
-4.60% |
54.440 |
51.934 |
0.009 |
-4.60% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/65
|
-4.60% |
95.110 |
90.733 |
0.004 |
-4.61% |
0.004 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<16, int>
|
-4.60% |
54.436 |
51.934 |
0.001 |
-4.60% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC2
|
-4.55% |
13.767 |
13.141 |
0.001 |
-0.10% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_1D_RAW/5001
|
-4.55% |
348.675 |
332.817 |
2.991 |
-3.54% |
2.991 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC2
|
-4.54% |
13.766 |
13.140 |
0.001 |
-4.54% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC31
|
-4.47% |
70.084 |
66.954 |
0.005 |
-4.46% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint32_t_
|
-4.44% |
19407.824 |
18546.628 |
55.604 |
-3.87% |
55.604 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint16_t_
|
-4.34% |
9845.563 |
9417.836 |
17.892 |
-4.68% |
17.892 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/16
|
-4.31% |
59.933 |
57.349 |
0.162 |
6.56% |
0.162 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/HPCCG/HPCCG
Profile
|
-4.31% |
3.919 |
3.750 |
0.042 |
-4.22% |
0.042 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/5001
|
-4.31% |
436.348 |
417.552 |
2.570 |
-4.68% |
2.570 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint8_t_
|
-4.30% |
2872.412 |
2748.988 |
9.966 |
-4.49% |
9.966 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint8_t_
|
-4.27% |
19802.631 |
18956.188 |
56.746 |
-4.46% |
56.746 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/171
|
-4.27% |
14.214 |
13.607 |
0.019 |
-4.45% |
0.019 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/999
|
-4.23% |
1811.212 |
1734.601 |
0.091 |
-4.23% |
0.091 |
|
SingleSource/Benchmarks/Misc/flops-5
Profile
|
-4.17% |
2.021 |
1.937 |
0.001 |
-4.16% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/999
|
-4.15% |
3594.920 |
3445.821 |
0.207 |
-4.14% |
0.207 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/256
|
-4.07% |
935.524 |
897.424 |
0.067 |
-4.08% |
0.067 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC31
|
-4.04% |
61.945 |
59.443 |
0.004 |
-4.04% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC32
|
-4.01% |
31.288 |
30.033 |
0.002 |
-4.00% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC3
|
-4.01% |
15.644 |
15.018 |
0.000 |
-4.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/65
|
-3.99% |
94.497 |
90.729 |
0.002 |
-3.98% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_uint8_t_
|
-3.97% |
96165.092 |
92343.069 |
3.138 |
-3.97% |
3.138 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC32
|
-3.97% |
63.201 |
60.695 |
0.003 |
-3.96% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/256
|
-3.95% |
221.499 |
212.741 |
0.004 |
-3.96% |
0.004 |
|
MultiSource/Benchmarks/TSVC/Recurrences-dbl/Recurrences-dbl
Profile
|
-3.95% |
10.341 |
9.933 |
0.103 |
-4.10% |
0.103 |
|
MultiSource/Benchmarks/sim/sim
Profile
|
-3.92% |
9.709 |
9.328 |
0.001 |
-3.84% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_cond_load_autovec_int64_t_
|
-3.87% |
552944.850 |
531542.906 |
566.988 |
-3.82% |
566.988 |
|
MicroBenchmarks/LCALS/SubsetBLambdaLoops/lcalsBLambda.test:BM_MULADDSUB_LAMBDA/171
|
-3.87% |
0.429 |
0.412 |
0.003 |
-1.35% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC31
|
-3.87% |
93.276 |
89.670 |
0.020 |
-4.46% |
0.020 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_SUM_RAW/5001
|
-3.81% |
18.408 |
17.707 |
0.241 |
2.08% |
0.241 |
|
External/SPEC/CFP2017rate/544.nab_r/544.nab_r
Profile
|
-3.80% |
476.131 |
458.060 |
0.168 |
-4.15% |
0.168 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/171
|
-3.78% |
14.171 |
13.635 |
0.011 |
-4.30% |
0.011 |
|
External/SPEC/CFP2017rate/519.lbm_r/519.lbm_r
Profile
|
-3.78% |
199.766 |
192.224 |
1.379 |
-4.21% |
1.379 |
|
External/SPEC/CINT2017rate/523.xalancbmk_r/523.xalancbmk_r
Profile
|
-3.74% |
244.047 |
234.908 |
0.827 |
-2.51% |
0.827 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC32
|
-3.73% |
49.434 |
47.589 |
0.021 |
-4.92% |
0.021 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/5001
|
-3.70% |
436.883 |
420.734 |
3.643 |
-1.87% |
3.643 |
|
SingleSource/Benchmarks/Shootout/Shootout-matrix
Profile
|
-3.69% |
3.863 |
3.721 |
0.000 |
-3.68% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/256
|
-3.64% |
514.355 |
495.611 |
0.025 |
-3.65% |
0.025 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC31
|
-3.62% |
60.377 |
58.190 |
0.007 |
-3.46% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC64
|
-3.61% |
69.458 |
66.952 |
0.003 |
-3.61% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC64
|
-3.60% |
69.454 |
66.953 |
0.004 |
-3.60% |
0.004 |
|
SingleSource/Benchmarks/BenchmarkGame/n-body
Profile
|
-3.59% |
2.732 |
2.634 |
0.000 |
21.70% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC63
|
-3.57% |
70.081 |
67.577 |
0.009 |
-3.59% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC63
|
-3.57% |
70.082 |
67.579 |
0.008 |
-3.57% |
0.008 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, EqZero, First>
|
-3.53% |
3345.861 |
3227.657 |
3.357 |
-3.55% |
3.357 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_int32_t_
|
-3.51% |
649072.286 |
626287.146 |
304.300 |
-2.92% |
304.300 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/256
|
-3.48% |
1053.884 |
1017.191 |
4.687 |
-4.69% |
4.687 |
|
MultiSource/Benchmarks/nbench/nbench
Profile
|
-3.43% |
6.107 |
5.897 |
0.001 |
-3.75% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC127
|
-3.42% |
2407.171 |
2324.760 |
20.980 |
-4.20% |
20.980 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC31
|
-3.39% |
31.089 |
30.034 |
0.001 |
-3.71% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC64
|
-3.38% |
111.386 |
107.622 |
0.004 |
-3.38% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint32_t_
|
-3.36% |
11250.421 |
10872.089 |
17.887 |
-4.15% |
17.887 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, EqZero, Last>
|
-3.35% |
7051.778 |
6815.854 |
53.657 |
-3.36% |
53.657 |
|
MultiSource/Benchmarks/Rodinia/pathfinder/pathfinder
Profile
|
-3.33% |
1.263 |
1.221 |
0.008 |
-2.91% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint16_t_To_uint8_t_
|
-3.22% |
4514.943 |
4369.494 |
8.884 |
-3.27% |
8.884 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/999
|
-3.15% |
514.950 |
498.733 |
0.015 |
-3.16% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC1
|
-3.13% |
20.025 |
19.398 |
0.001 |
-3.13% |
0.001 |
|
SingleSource/Benchmarks/Shootout/Shootout-lists
Profile
|
-3.12% |
11.316 |
10.963 |
0.002 |
-3.09% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/1000
|
-3.08% |
5020171.460 |
4865539.333 |
630.444 |
-3.07% |
630.444 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<4, int>
|
-2.99% |
15.803 |
15.330 |
0.000 |
-3.64% |
0.000 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/CoMD/CoMD
Profile
|
-2.93% |
9.909 |
9.618 |
0.008 |
-2.83% |
0.008 |
|
MultiSource/Benchmarks/TSVC/Symbolics-flt/Symbolics-flt
Profile
|
-2.88% |
4.886 |
4.745 |
0.026 |
-0.18% |
0.026 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/999
|
-2.83% |
1013.720 |
985.062 |
0.012 |
-2.84% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC1
|
-2.78% |
22.526 |
21.901 |
0.001 |
-2.77% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/512
|
-2.77% |
6659.808 |
6475.072 |
12.718 |
-2.56% |
12.718 |
|
MultiSource/Benchmarks/FreeBench/mason/mason
Profile
|
-2.70% |
0.553 |
0.538 |
0.000 |
-2.74% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/128
|
-2.65% |
438.123 |
426.513 |
0.603 |
-2.95% |
0.603 |
|
MultiSource/Applications/JM/lencod/lencod
Profile
|
-2.64% |
32.717 |
31.852 |
0.028 |
-2.11% |
0.028 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC63
|
-2.61% |
120.152 |
117.010 |
0.002 |
-2.61% |
0.002 |
|
SingleSource/Benchmarks/Misc-C++/oopack_v1p8
Profile
|
-2.59% |
0.480 |
0.467 |
0.000 |
-9.96% |
0.000 |
|
MultiSource/Benchmarks/FreeBench/pcompress2/pcompress2
Profile
|
-2.58% |
0.404 |
0.393 |
0.001 |
-2.77% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC32
|
-2.57% |
24.405 |
23.776 |
0.001 |
-2.58% |
0.001 |
|
MultiSource/Benchmarks/TSVC/GlobalDataFlow-flt/GlobalDataFlow-flt
Profile
|
-2.57% |
6.589 |
6.420 |
0.064 |
-3.57% |
0.064 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC32
|
-2.56% |
24.403 |
23.778 |
0.001 |
-2.56% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC31
|
-2.56% |
24.402 |
23.777 |
0.003 |
-2.57% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/10
|
-2.56% |
48.805 |
47.556 |
0.018 |
2.47% |
0.018 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC31
|
-2.56% |
24.403 |
23.779 |
0.002 |
-2.56% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint32_t_
|
-2.55% |
7077.713 |
6897.242 |
1.126 |
-2.54% |
1.126 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, GreaterThanZero, Last>
|
-2.54% |
8311.106 |
8099.793 |
2.104 |
-2.36% |
2.104 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/256
|
-2.48% |
1787.474 |
1743.155 |
2.251 |
0.55% |
2.251 |
|
MultiSource/Benchmarks/mafft/pairlocalalign
Profile
|
-2.41% |
93.971 |
91.707 |
0.055 |
-2.50% |
0.055 |
|
MultiSource/Benchmarks/FreeBench/fourinarow/fourinarow
Profile
|
-2.39% |
0.651 |
0.635 |
0.000 |
-2.39% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC63
|
-2.37% |
130.134 |
127.054 |
0.173 |
-2.39% |
0.173 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/32
|
-2.36% |
166197.589 |
162273.149 |
184.009 |
-2.36% |
184.009 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC63
|
-2.34% |
106.995 |
104.496 |
0.005 |
-2.34% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC64
|
-2.32% |
108.255 |
105.746 |
0.003 |
-2.31% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_uint8_t_
|
-2.27% |
504655.804 |
493223.853 |
98.715 |
-2.28% |
98.715 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INNER_PROD_RAW/44217
|
-2.23% |
363.500 |
355.377 |
2.868 |
-1.11% |
2.868 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/44217
|
-2.19% |
4357.653 |
4262.101 |
8.266 |
-1.60% |
8.266 |
|
SingleSource/Benchmarks/Misc/flops-1
Profile
|
-2.17% |
9.001 |
8.806 |
0.000 |
-2.15% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopFrom_uint64_t_To_uint16_t_
|
-2.15% |
14882.707 |
14562.435 |
103.549 |
-1.84% |
103.549 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC128
|
-2.09% |
119.520 |
117.016 |
0.006 |
-2.10% |
0.006 |
|
SingleSource/Benchmarks/Misc-C++/Large/ray
Profile
|
-2.09% |
12.103 |
11.849 |
0.001 |
-2.08% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC127
|
-2.09% |
120.141 |
117.632 |
0.003 |
-2.09% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC127
|
-2.08% |
120.146 |
117.642 |
0.002 |
-2.08% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_int64_t_
|
-2.05% |
1447730.023 |
1418096.600 |
216.496 |
-2.00% |
216.496 |
|
MultiSource/Benchmarks/Bullet/bullet
Profile
|
-2.00% |
30.416 |
29.809 |
0.179 |
-2.04% |
0.179 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_EOS_RAW/171
|
-1.95% |
0.873 |
0.856 |
0.002 |
-1.70% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/44217
|
-1.93% |
4317.188 |
4233.854 |
5.964 |
-2.09% |
5.964 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, GreaterThanZero, None>
|
-1.92% |
29678.094 |
29107.707 |
6.210 |
-1.59% |
6.210 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/171
|
-1.89% |
6.925 |
6.794 |
0.004 |
-1.88% |
0.004 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, LessThanZero, Mid>
|
-1.86% |
8663.799 |
8502.220 |
3.778 |
-1.82% |
3.778 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/SimpleMOC/SimpleMOC
Profile
|
-1.86% |
10.437 |
10.242 |
0.012 |
-1.56% |
0.012 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, EqZero, Mid>
|
-1.86% |
8658.580 |
8497.933 |
15.950 |
-1.84% |
15.950 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/256
|
-1.84% |
272.829 |
267.813 |
0.021 |
-1.84% |
0.021 |
|
External/SPEC/CINT2017rate/531.deepsjeng_r/531.deepsjeng_r
Profile
|
-1.80% |
259.982 |
255.292 |
0.553 |
-1.85% |
0.553 |
|
MultiSource/Applications/sgefa/sgefa
Profile
|
-1.76% |
0.574 |
0.563 |
0.003 |
-1.75% |
0.003 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, LessThanZero, None>
|
-1.76% |
37699.479 |
37036.519 |
47.803 |
-1.44% |
47.803 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_EOS_LAMBDA/171
|
-1.75% |
0.872 |
0.857 |
0.000 |
-1.61% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint64_t_
|
-1.75% |
26315.492 |
25855.485 |
17.718 |
-1.62% |
17.718 |
|
MultiSource/Benchmarks/ASC_Sequoia/AMGmk/AMGmk
Profile
|
-1.73% |
33.351 |
32.773 |
0.063 |
-0.86% |
0.063 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, LessThanZero, Mid>
|
-1.71% |
4570.721 |
4492.479 |
0.955 |
-1.72% |
0.955 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/51
|
-1.68% |
148.289 |
145.792 |
0.007 |
-1.70% |
0.007 |
|
MultiSource/Benchmarks/VersaBench/ecbdes/ecbdes
Profile
|
-1.68% |
5.141 |
5.055 |
0.001 |
-1.64% |
0.001 |
|
MicroBenchmarks/Builtins/Int128/Builtins.test:BM_RemainderIntrinsic128UniformDivisor<__int128_t>
|
-1.65% |
66.733 |
65.633 |
0.299 |
-0.90% |
0.299 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, GreaterThanZero, None>
|
-1.64% |
37108.091 |
36501.085 |
10.674 |
-1.81% |
10.674 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_in_loop_arith_novec_int64_t_
|
-1.62% |
1028535.474 |
1011916.420 |
548.902 |
-1.58% |
548.902 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/10
|
-1.58% |
57.862 |
56.948 |
0.001 |
-0.18% |
0.001 |
|
SingleSource/Benchmarks/Misc/mandel-2
Profile
|
-1.57% |
2.536 |
2.496 |
0.000 |
-1.55% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/171
|
-1.56% |
6.916 |
6.808 |
0.006 |
-1.69% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint16_t_To_uint32_t_
|
-1.56% |
13508.904 |
13298.626 |
28.627 |
-1.37% |
28.627 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, GreaterThanZero, None>
|
-1.49% |
45003.499 |
44334.931 |
27.027 |
-1.79% |
27.027 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC127
|
-1.44% |
220.295 |
217.124 |
0.010 |
-1.43% |
0.010 |
|
MultiSource/Benchmarks/TSVC/LoopRerolling-dbl/LoopRerolling-dbl
Profile
|
-1.38% |
16.181 |
15.957 |
0.069 |
-0.24% |
0.069 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/51
|
-1.36% |
229.011 |
225.894 |
0.015 |
-1.36% |
0.015 |
|
MultiSource/Benchmarks/tramp3d-v4/tramp3d-v4
Profile
|
-1.36% |
1.073 |
1.059 |
0.001 |
-1.57% |
0.001 |
|
External/SPEC/CFP2017rate/511.povray_r/511.povray_r
Profile
|
-1.36% |
33.950 |
33.489 |
0.002 |
-0.88% |
0.002 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, LessThanZero, Mid>
|
-1.35% |
56525.811 |
55760.304 |
4.024 |
-1.36% |
4.024 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC63
|
-1.33% |
47.562 |
46.930 |
0.001 |
2.74% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, GreaterThanZero, Mid>
|
-1.33% |
4559.320 |
4498.893 |
6.642 |
-1.24% |
6.642 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC127
|
-1.27% |
197.112 |
194.605 |
0.008 |
-1.27% |
0.008 |
|
MultiSource/Benchmarks/Olden/health/health
Profile
|
-1.27% |
1.585 |
1.565 |
0.002 |
-1.67% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC128
|
-1.26% |
198.347 |
195.851 |
0.010 |
-1.27% |
0.010 |
|
SingleSource/Benchmarks/BenchmarkGame/puzzle
Profile
|
-1.24% |
0.864 |
0.854 |
0.002 |
-1.75% |
0.002 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<8, LessThanZero, Mid>
|
-1.22% |
19470.578 |
19233.562 |
13.168 |
-1.03% |
13.168 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<7, EqZero, None>
|
-1.20% |
27197.784 |
26870.368 |
19.278 |
-1.14% |
19.278 |
|
MultiSource/Benchmarks/MallocBench/cfrac/cfrac
Profile
|
-1.19% |
2.778 |
2.745 |
0.001 |
-1.25% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/512
|
-1.16% |
3543.375 |
3502.138 |
15.451 |
-2.29% |
15.451 |
|
MultiSource/Benchmarks/TSVC/Searching-flt/Searching-flt
Profile
|
-1.16% |
4.128 |
4.080 |
0.011 |
-0.10% |
0.011 |
|
SingleSource/Benchmarks/SmallPT/smallpt
Profile
|
-1.13% |
30.044 |
29.706 |
0.001 |
-1.08% |
0.001 |
|
SingleSource/Benchmarks/Shootout/Shootout-heapsort
Profile
|
-1.11% |
22.239 |
21.993 |
0.066 |
-0.22% |
0.066 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, LessThanZero, Mid>
|
-1.11% |
23749.484 |
23487.029 |
2.046 |
-0.34% |
2.046 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, EqZero, Mid>
|
-1.10% |
2758.936 |
2728.673 |
1.027 |
-0.57% |
1.027 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, LessThanZero, Last>
|
-1.08% |
56412.427 |
55802.350 |
231.720 |
-0.43% |
231.720 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinhf_autovec_float_
|
-1.08% |
2242.062 |
2217.907 |
0.411 |
-1.10% |
0.411 |
|
MultiSource/Benchmarks/TSVC/InductionVariable-flt/InductionVariable-flt
Profile
|
-1.07% |
11.385 |
11.263 |
0.045 |
-0.96% |
0.045 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinhf_novec_float_
|
-1.05% |
2241.821 |
2218.321 |
0.305 |
-1.05% |
0.305 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/16
|
-1.01% |
85.566 |
84.703 |
0.158 |
12.12% |
0.158 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_int64_t_
|
-1.00% |
814460.754 |
806314.140 |
2028.488 |
-0.88% |
2028.488 |