![]() ![]() NVIDIA reserves the right to make corrections, modifications, enhancements, improvements, and any other changes to this document, at any time without notice.Ĭustomer should obtain the latest relevant information before placing orders and should verify that such information is current and complete. This document is not a commitment to develop, release, or deliver any Material (defined below), code, or functionality. NVIDIA shall have no liability for the consequences or use of such information or for any infringement of patents or other rights of third parties that may result from its use. NVIDIA Corporation (“NVIDIA”) makes no representations or warranties, expressed or implied, as to the accuracy or completeness of the information contained in this document and assumes no responsibility for any errors contained herein. This document is provided for information purposes only and shall not be regarded as a warranty of a certain functionality, condition, or quality of a product. 200,000)ĭecrement the number of displayed points by 8,000 (down to min. Increment the number of displayed points by 8,000 (max. ![]() Reset the number of Sobol’ dimensions to 1 and regenerate Increment the number of Sobol’ dimensions and regenerate Rotate the negative Z-axis up, right, down and left respectively Generate new set of random nos and display on a cartesian plane (Plane) Generate new set of random nos and display as cartesian coordinates (cuBe/Box) Generate new set of random nos and display on a spherical surface (shEll) Generate new set of random nos and display as spherical coordinates (Sphere) The Z axis is drawn with red in the negative direction and cyan positive. The Y axis is drawn with green in the negative direction and magenta positive. The X axis is drawn with blue in the negative direction and yellow positive. The coordinates are normalized for a uniform distribution through the sphere. On creation, randomFog generates 200,000 random coordinates in spherical coordinate space (radius, angle rho, angle theta) with curand’s XORWOW algorithm. This is a graphical demo which does pseudo- and quasi- random numbers visualization produced by CURAND. The following keys can be used to control the output: This is a graphical demo which simulates an ocean height field using the CUFFT library, and renders the result using OpenGL. Where i=(number of CUDA devices > 0) to use for simulationĬompares simulation results running once on the default GPU and once on the CPU Number of bodies (>= 1) to run in simulation ![]() Use double precision floating point values for simulation For a small number of devices (4 or fewer) and a large enough number of bodies, bandwidth is not a bottleneck so we can achieve strong scaling across these devices. In this mode, the position and velocity data for all bodies are read from system memory using “zero copy” rather than from device memory. Adding “-numdevices=N” to the command line option will cause the sample to use N devices (if available) for simulation. Adding “-numbodies=num_of_bodies” to the command line will allow users to set # of bodies for simulation. It scales the n-body simulation across multiple GPUs in a single PC if available. This demo does an efficient all-pairs simulation of a gravitational n-body simulation in CUDA. BusGrind -a Runs all tests (pinned, unpinned, p2p enabled, p2p disabled) BusGrind -n -u 1 Runs only unpinned tests BusGrind -n -p 1 -e 1 Run all pinned and P2P tests Performs an intense shmoo of a large range of values Measures a user-specified range of values bandwidthTest -memory=pinned -mode=range -start=1024 -end=102400 -increment=1024 -dtohĬompute cumulative bandwidth on all the devices Test the bandwidth for device to host, host to device, and device to device transfersĮxample: measure the bandwidth of device to host pinned memory copies in the range 1024 Bytes to 102400 Bytes in 1024 Byte increments ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |