UPGRADE YOUR BROWSER

We have detected your current browser version is not the latest one. Xilinx.com uses the latest web technologies to bring you the best online experience possible. Please upgrade to a Xilinx.com supported browser:Chrome, Firefox, Internet Explorer 11, Safari. Thank you!

取消
显示结果 
搜索替代 
您的意思是: 
Xilinx Employee
Xilinx Employee
136 次查看
注册日期: ‎02-16-2012

MPSoC的linpack性能,在O3优化情况下,可以达到325MFLOPS。

MPSoC的linpack性能,在O3优化情况下,可以达到325MFLOPS。

root@vcu-zcu106-2017_4:/media/card# ./linpack_linux_debug.elf
Memory required: 315K.
LINPACK benchmark, Double precision.
Machine precision: 15 digits.
Array size 200 X 200.
Average rolled and unrolled performance:

Reps Time(s) DGEFA DGESL OVERHEAD KFLOPS
----------------------------------------------------
32 0.80 88.22% 2.66% 9.12% 60224.260
64 1.61 88.22% 2.66% 9.12% 60222.734
128 3.21 88.22% 2.66% 9.12% 60222.734
256 6.42 88.22% 2.66% 9.12% 60223.745
512 12.85 88.22% 2.66% 9.12% 60223.182


root@vcu-zcu106-2017_4:/media/card# ./linpack_linux_release_o2.elf
Memory required: 315K.
LINPACK benchmark, Double precision.
Machine precision: 15 digits.
Array size 200 X 200.
Average rolled and unrolled performance:

Reps Time(s) DGEFA DGESL OVERHEAD KFLOPS
----------------------------------------------------
64 0.53 90.14% 2.83% 7.03% 179884.802
128 1.05 90.14% 2.83% 7.03% 179895.664
256 2.10 90.14% 2.83% 7.03% 179914.444
512 4.20 90.14% 2.83% 7.03% 179980.620
1024 8.40 90.14% 2.83% 7.03% 179978.639
2048 16.81 90.14% 2.83% 7.03% 179972.535

root@vcu-zcu106-2017_4:/media/card#
root@vcu-zcu106-2017_4:/media/card#
root@vcu-zcu106-2017_4:/media/card# ./linpack_linux_release_o3.elf
Memory required: 315K.
LINPACK benchmark, Double precision.
Machine precision: 15 digits.
Array size 200 X 200.
Average rolled and unrolled performance:

Reps Time(s) DGEFA DGESL OVERHEAD KFLOPS
----------------------------------------------------
128 0.60 87.66% 2.93% 9.41% 325459.745
256 1.19 87.66% 2.93% 9.41% 325488.069

512 2.38 87.66% 2.93% 9.41% 325492.438
1024 4.77 87.66% 2.93% 9.41% 325488.521
2048 9.54 87.66% 2.93% 9.41% 325557.165
4096 19.07 87.66% 2.93% 9.41% 325609.346