gaussian-splatting-my/envs/gaussian_splatting/Library/share/man/man3/hwlocality_cuda.3

.TH "hwlocality_cuda" 3 "Thu Sep 7 2023" "Version 2.9.3" "Hardware Locality (hwloc)" \" -*- nroff -*-
.ad l
.nh
.SH NAME
hwlocality_cuda \- Interoperability with the CUDA Driver API
.SH SYNOPSIS
.br
.PP
.SS "Functions"

.in +1c
.ti -1c
.RI "static int \fBhwloc_cuda_get_device_pci_ids\fP (\fBhwloc_topology_t\fP topology, CUdevice cudevice, int *domain, int *bus, int *dev)"
.br
.ti -1c
.RI "static int \fBhwloc_cuda_get_device_cpuset\fP (\fBhwloc_topology_t\fP topology, CUdevice cudevice, \fBhwloc_cpuset_t\fP set)"
.br
.ti -1c
.RI "static \fBhwloc_obj_t\fP \fBhwloc_cuda_get_device_pcidev\fP (\fBhwloc_topology_t\fP topology, CUdevice cudevice)"
.br
.ti -1c
.RI "static \fBhwloc_obj_t\fP \fBhwloc_cuda_get_device_osdev\fP (\fBhwloc_topology_t\fP topology, CUdevice cudevice)"
.br
.ti -1c
.RI "static \fBhwloc_obj_t\fP \fBhwloc_cuda_get_device_osdev_by_index\fP (\fBhwloc_topology_t\fP topology, unsigned idx)"
.br
.in -1c
.SH "Detailed Description"
.PP 
This interface offers ways to retrieve topology information about CUDA devices when using the CUDA Driver API\&. 
.SH "Function Documentation"
.PP 
.SS "static int hwloc_cuda_get_device_cpuset (\fBhwloc_topology_t\fP topology, CUdevice cudevice, \fBhwloc_cpuset_t\fP set)\fC [inline]\fP, \fC [static]\fP"

.PP
Get the CPU set of processors that are physically close to device \fCcudevice\fP\&. Store in \fCset\fP the CPU-set describing the locality of the CUDA device \fCcudevice\fP\&.
.PP
Topology \fCtopology\fP and device \fCcudevice\fP must match the local machine\&. I/O devices detection and the CUDA component are not needed in the topology\&.
.PP
The function only returns the locality of the device\&. If more information about the device is needed, OS objects should be used instead, see \fBhwloc_cuda_get_device_osdev()\fP and \fBhwloc_cuda_get_device_osdev_by_index()\fP\&.
.PP
This function is currently only implemented in a meaningful way for Linux; other systems will simply get a full cpuset\&.
.PP
\fBReturns\fP
.RS 4
0 on success\&. 
.PP
-1 on error, for instance if device information could not be found\&. 
.RE
.PP

.SS "static \fBhwloc_obj_t\fP hwloc_cuda_get_device_osdev (\fBhwloc_topology_t\fP topology, CUdevice cudevice)\fC [inline]\fP, \fC [static]\fP"

.PP
Get the hwloc OS device object corresponding to CUDA device \fCcudevice\fP\&. 
.PP
\fBReturns\fP
.RS 4
The hwloc OS device object that describes the given CUDA device \fCcudevice\fP\&. 
.PP
\fCNULL\fP if none could be found\&.
.RE
.PP
Topology \fCtopology\fP and device \fCcudevice\fP must match the local machine\&. I/O devices detection and the CUDA component must be enabled in the topology\&. If not, the locality of the object may still be found using \fBhwloc_cuda_get_device_cpuset()\fP\&.
.PP
\fBNote\fP
.RS 4
This function cannot work if PCI devices are filtered out\&.
.PP
The corresponding hwloc PCI device may be found by looking at the result parent pointer (unless PCI devices are filtered out)\&. 
.RE
.PP

.SS "static \fBhwloc_obj_t\fP hwloc_cuda_get_device_osdev_by_index (\fBhwloc_topology_t\fP topology, unsigned idx)\fC [inline]\fP, \fC [static]\fP"

.PP
Get the hwloc OS device object corresponding to the CUDA device whose index is \fCidx\fP\&. 
.PP
\fBReturns\fP
.RS 4
The hwloc OS device object describing the CUDA device whose index is \fCidx\fP\&. 
.PP
\fCNULL\fP if none could be found\&.
.RE
.PP
The topology \fCtopology\fP does not necessarily have to match the current machine\&. For instance the topology may be an XML import of a remote host\&. I/O devices detection and the CUDA component must be enabled in the topology\&.
.PP
\fBNote\fP
.RS 4
The corresponding PCI device object can be obtained by looking at the OS device parent object (unless PCI devices are filtered out)\&.
.PP
This function is identical to \fBhwloc_cudart_get_device_osdev_by_index()\fP\&. 
.RE
.PP

.SS "static int hwloc_cuda_get_device_pci_ids (\fBhwloc_topology_t\fP topology, CUdevice cudevice, int * domain, int * bus, int * dev)\fC [inline]\fP, \fC [static]\fP"

.PP
Return the domain, bus and device IDs of the CUDA device \fCcudevice\fP\&. Device \fCcudevice\fP must match the local machine\&.
.PP
\fBReturns\fP
.RS 4
0 on success\&. 
.PP
-1 on error, for instance if device information could not be found\&. 
.RE
.PP

.SS "static \fBhwloc_obj_t\fP hwloc_cuda_get_device_pcidev (\fBhwloc_topology_t\fP topology, CUdevice cudevice)\fC [inline]\fP, \fC [static]\fP"

.PP
Get the hwloc PCI device object corresponding to the CUDA device \fCcudevice\fP\&. 
.PP
\fBReturns\fP
.RS 4
The hwloc PCI device object describing the CUDA device \fCcudevice\fP\&. 
.PP
\fCNULL\fP if none could be found\&.
.RE
.PP
Topology \fCtopology\fP and device \fCcudevice\fP must match the local machine\&. I/O devices detection must be enabled in topology \fCtopology\fP\&. The CUDA component is not needed in the topology\&. 
.SH "Author"
.PP 
Generated automatically by Doxygen for Hardware Locality (hwloc) from the source code\&.