|
|
Heat Diffusion Simulation on GPU
Hradecký, Michal ; Vašíček, Zdeněk (referee) ; Jaroš, Jiří (advisor)
This thesis deals with the simulation of heat diffusion in human tissues. The proposed algorithm uses a finite-difference time-domain method, which is applied on the governing equation describing the system. A modern graphics card is used to accelerate the simulation. The performance achieved on the GPU card is compared with the implementation exploiting a modern multicore CPU. The output of this thesis is a set of differently optimized algorithms targeted on NVIDIA graphics cards. The experimental results reveal that the use of shared memory is contraproductive and the best performance is achieved by a register based implementation. The overall speedup of 18.5 was reached when comparing a NVIDIA GeForce GTX 580 with a quad-core Intel Core i7 920 CPU. This nicely corresponds with the theoretical capabilities of both architectures.
|
|
|
Development and Programming of Low Power Cluster
Hradecký, Michal ; Nikl, Vojtěch (referee) ; Jaroš, Jiří (advisor)
This thesis deals with the building and programming of a low power cluster composed of Hardkernel Odroid XU4 kits based on ARM Cortex A15 and Cortex A7 chips. The goal was to design a simple cluster composed of multiple kits and run a set of benchmarks to analyze performance and power consumption. The test set consisted of HPL and Stream benchmarks and various tests for the MPI interface. The overall performance of the cluster composed of four kits in HPL benchmark was measured 23~GFLOP/s in double-precision. During this test, the cluster showed power efficiency about 0.58~GFLOP/W. The work also describes the installation of PBS Torque scheduler and HPC software build and installation framework EasyBuild on 32-bit ARM platform. The comparison with Anselm supercomputer showed that Odroid cluster is as effiecient as large supercomputer but with slightly higher price.
|
|
|
Development and Programming of Low Power Cluster
Hradecký, Michal ; Nikl, Vojtěch (referee) ; Jaroš, Jiří (advisor)
This thesis deals with the building and programming of a low power cluster composed of Hardkernel Odroid XU4 kits based on ARM Cortex A15 and Cortex A7 chips. The goal was to design a simple cluster composed of multiple kits and run a set of benchmarks to analyze performance and power consumption. The test set consisted of HPL and Stream benchmarks and various tests for the MPI interface. The overall performance of the cluster composed of four kits in HPL benchmark was measured 23~GFLOP/s in double-precision. During this test, the cluster showed power efficiency about 0.58~GFLOP/W. The work also describes the installation of PBS Torque scheduler and HPC software build and installation framework EasyBuild on 32-bit ARM platform. The comparison with Anselm supercomputer showed that Odroid cluster is as effiecient as large supercomputer but with slightly higher price.
|
|
|
Heat Diffusion Simulation on GPU
Hradecký, Michal ; Vašíček, Zdeněk (referee) ; Jaroš, Jiří (advisor)
This thesis deals with the simulation of heat diffusion in human tissues. The proposed algorithm uses a finite-difference time-domain method, which is applied on the governing equation describing the system. A modern graphics card is used to accelerate the simulation. The performance achieved on the GPU card is compared with the implementation exploiting a modern multicore CPU. The output of this thesis is a set of differently optimized algorithms targeted on NVIDIA graphics cards. The experimental results reveal that the use of shared memory is contraproductive and the best performance is achieved by a register based implementation. The overall speedup of 18.5 was reached when comparing a NVIDIA GeForce GTX 580 with a quad-core Intel Core i7 920 CPU. This nicely corresponds with the theoretical capabilities of both architectures.
|
guest ::
RSS feed.