![]() ![]() This testing highlights how GPU hardware has clear advantage over CPU for parallelised computing using TUFLOW HPC. Please refer to the paragraph below for discussion relating to GPU.Įven through one CPU core is typically faster than one GPU CUDA core, the runtime of the HPC solver on i7-5960X using 8 CPU cores is much slower than that on the NVIDIA GeForce GTX 1080 Ti GPU card using 3584 CUDA cores. This section does not consider TUFLOW HPC simulation speed with GPU acceleration. Testing across a large range of models has shown this result trend typically varies from 6 to 10 CPU depending on the features included in a model. For this benchmark test 8 CPU cores were necessary for TUFLOW HPC to achieve the same speed as a single CPU using TUFLOW Classic. The larger timestep used by TUFLOW Classic helps it run faster than TUFLOW HPC if both are limited to using a single CPU.Īs expected, TUFLOW HPC simulations run faster as the number of CPU cores increase. For this benchmark test the model ran using a 6 second timestep in TUFLOW Classic (implicit), while the adaptive timestep used by TUFLOW HPC (explicit) ranged from 1.7 to 2.3 seconds. Computationally, implicit schemes can achieve a stable solution at a larger time step comparable to explicit schemes. Explicit solver are well suited to code parallelisation. ![]() As such, TUFLOW Classic can only run on a single CPU. Implicit schemes are inefficient to parallelise. TUFLOW Classic uses an implicit solution scheme. The results show the runtime of TUFLOW Classic is much faster than TUFLOW HPC when both are run using a single (1) CPU core. Simulation Speed-up (relative to TUFLOW Classic)ĭiscussions TUFLOW Classic vs TUFLOW HPC on CPU ![]() The TUFLOW HPC simulation was also run using GPU hardware. These TUFLOW HPC simulations were tested for a range of CPU core multiples (from one through to eight). The table below presents runtimes for the same model run using TUFLOW Classic and TUFLOW HPC on CPU. GPU: NVIDIA GeForce GTX 1080 Ti GPU card (3584 CUDA cores).This provides access to 8 physical CPU cores. CPU: Intel(R) Core(TM) i7-5960X CPU 3.00GHz processor.The simulations were conducted on a computer with the following hardware: Refer to the FMA Challenge Model 2 wiki page for a full description of the model. This translates to 182,000 cells overall, of which, approximately 115,000 cells are wet at the peak of the flood. The model includes a coastal floodplain with two ocean outlets and simulates a flood over a 72 hour period. The benchmark model used for this testing is based on a FMA Challenge Model 2 issued prior to the 2012 Flood Managers Association (FMA) Conference in Sacramento, USA. -25 of Rapid and Accurate Stormwater Drainage Assessments Using GPU Technology (IECA-SQ Conference - Brisbane, Australia).Floating Point Operations per Second (FLOPS) on wikipedia.For this reason, rather than discussing hardware components generally hardware benchmarks specific to TUFLOW provide the best indication of the relative performance of systems. It includes things such as the instruction set architecture, microarchitecture, precision of computations, the TUFLOW model design and size (number of cells). The speed at which TUFLOW HPC can solve depends on more than just the number of cores and processor speed. The shear number of CUDA cores however typically mean simulation using GPU hardware will be faster than CPU. In a one-for-one comparison CPU cores are typically faster than GPU cores. At the time of writing both the i7-8700k and GTX 1080ti are high end desktop hardware components. By contrast a GeForce GTX 1080ti has a total of 3,584 CUDA cores (running at up to 1.58 GHz). For example a i7-8700 Intel CPU has 6 CPU cores (running at up to 4.7GHz). This code architecture has been implemented to increase simulation speed.īoth CPU and GPU typically have multiple cores, however, GPU devices typically have a significantly larger number. As it's name suggests, TUFLOW HPC has been parallelised to enable simulation execution using multiple cores. ![]() This page discusses and compares simulation speed using both sets of computer hardware. TUFLOW HPC (Heavily Parallelised Compute) has the ability to run on both CPU and Nvidia CUDA compatible GPU devices. 5.3 TUFLOW HPC GPU Speed-up vs Model Size.5.1 TUFLOW Classic vs TUFLOW HPC on CPU. ![]()
0 Comments
Leave a Reply. |
Details
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |