| /linux/drivers/gpu/drm/amd/amdkfd/ |
| H A D | Kconfig | 25 based memory management on most GFXv9 GPUs, set the module
32 Enable peer-to-peer (P2P) communication between AMD GPUs over
34 applications and libraries by enabling GPUs to access data directly
35 in peer GPUs' memory without intermediate copies in system memory.
38 GPUs with large memory BARs that expose the entire VRAM in PCIe bus
39 address space within the physical address limits of the GPUs.
|
| /linux/drivers/gpu/drm/panthor/ |
| H A D | Kconfig | 4 tristate "Panthor (DRM support for ARM Mali CSF-based GPUs)"
18 DRM driver for ARM Mali CSF-based GPUs.
20 This driver is for Mali (or Immortalis) Valhall Gxxx GPUs.
23 be supported with the panfrost driver as they are not CSF GPUs.
|
| /linux/drivers/gpu/drm/tyr/ |
| H A D | Kconfig | 4 tristate "Tyr (Rust DRM support for ARM Mali CSF-based GPUs)"
12 Rust DRM driver for ARM Mali CSF-based GPUs.
14 This driver is for Mali (or Immortalis) Valhall Gxxx GPUs.
17 be supported with the panfrost driver as they are not CSF GPUs.
|
| /linux/Documentation/gpu/amdgpu/ |
| H A D | flashing.rst | 7 Flashing the dGPU integrated firmware image (IFWI) is supported by GPUs that
8 use the PSP to orchestrate the update (Navi3x or newer GPUs).
9 For supported GPUs, `amdgpu` will export a series of sysfs files that can be
21 On GPUs that support flashing an updated USB-C PD firmware image, the process
|
| /linux/Documentation/gpu/nova/ |
| H A D | index.rst | 8 nova-drm and intends to supersede the nouveau driver for NVIDIA GPUs based on
21 The nova-core driver is the core driver for NVIDIA GPUs based on GSP. nova-core,
22 as the 1st level driver, provides an abstraction around the GPUs hard- and
|
| /linux/Documentation/accel/ |
| H A D | introduction.rst | 46 Because this type of devices can be an IP inside GPUs or have similar
47 characteristics as those of GPUs, the accel subsystem will use the
57 Differentiation from GPUs
62 differentiated from GPUs by using a new major number and new device char files.
|
| /linux/drivers/gpu/nova-core/ |
| H A D | Kconfig | 11 GPUs based on the GPU System Processor (GSP). This is true for Turing
12 and later GPUs.
|
| H A D | driver.rs | 35 // TODO: Add an abstraction for this to support newer GPUs which may support
36 // larger DMA addresses. Limiting these GPUs to smaller address widths won't
48 // Modern NVIDIA GPUs will show up as either VGA or 3D controllers.
|
| /linux/drivers/gpu/drm/panfrost/ |
| H A D | Kconfig | 4 tristate "Panfrost (DRM support for ARM Mali Midgard/Bifrost GPUs)"
18 Bifrost (G3x, G5x, G7x) GPUs.
|
| /linux/Documentation/i2c/busses/ |
| H A D | i2c-nvidia-gpu.rst | 14 and later GPUs and it is used to communicate with Type-C controller on GPUs.
|
| /linux/drivers/gpu/vga/ |
| H A D | vga_switcheroo.c | 54 * * muxed: Dual GPUs with a multiplexer chip to switch outputs between GPUs.
55 * * muxless: Dual GPUs but only one of them is connected to outputs.
69 * DRM drivers register GPUs with vga_switcheroo, these are henceforth called
76 * there can thus be up to three clients: Two vga clients (GPUs) and one audio
78 * machines with more than two GPUs should they become available.
100 * so gpus are initially assigned VGA_SWITCHEROO_UNKNOWN_ID
133 * Prerequisite is the registration of two GPUs and a handler
137 * @registered_clients: number of registered GPUs
624 * have opened device files of the GPUs or the audio client. If the
630 * closed the device files of the GPUs and the audio client.
[all …]
|
| H A D | Kconfig | 10 Many laptops released in 2008/9/10 have two GPUs with a multiplexer
|
| /linux/Documentation/driver-api/ |
| H A D | edac.rst | 195 both CPUs and GPUs via custom xGMI links. Thus, the data fabric on the
198 The MI200 accelerators are data center GPUs. They have 2 data fabrics,
214 4 MI200 (Aldebaran) GPUs using xGMI.
228 systems by calling system specific ops for both CPUs and GPUs.
246 four MI200 (Aldebaran) GPUs using xGMI. This topology can be represented
|
| H A D | dma-buf.rst | 321 On GPUs this poses a problem, because current desktop compositor protocols on
327 faults on GPUs are limited to pure compute workloads.
329 Furthermore GPUs usually have shared resources between the 3D rendering and
373 GPUs do not have any impact. This allows us to keep using DMA fences internally
382 GPUs doesn't anything fundamentally new.
|
| /linux/Documentation/gpu/ |
| H A D | nouveau.rst | 7 The drm/nouveau driver provides support for a wide range of NVIDIA GPUs,
19 submission required for the proper functioning of NVIDIA GPUs under the
|
| /linux/include/uapi/linux/ |
| H A D | kfd_ioctl.h | 198 * unlimited number of GPUs.
426 * all later mappings on all GPUs will use this address
452 /* Map memory to one or more GPUs
474 /* Unmap memory from one or more GPUs
693 * @num_devices: [in/out] Number of GPUs used by process. Size of @devices array.
748 /* GPUs only read, allows replication */
752 /* GPUs mostly read, may allow similar optimizations as RO, but writes fault */
772 * GPU IDs are used to specify GPUs as preferred and prefetch locations.
878 * translations on GFXv9 and later AMD GPUs can return XNACK and retry
891 * differently. Furthermore, not all GPUs support changing the mode
[all …]
|
| /linux/Documentation/process/ |
| H A D | botching-up-ioctls.rst | 11 memory on completely different GPUs is a futile effort. So nowadays every
89 error handling paths - GPUs will die eventually in the oddmost corner cases
117 killable. GPUs just die and your users won't like you more if you hang their
130 GPUs do most everything asynchronously, so we have a need to time operations and
|
| /linux/include/linux/ |
| H A D | adreno-smmu-priv.h | 42 * @get_ttbr1_cfg: Get the TTBR1 config for the GPUs context-bank
43 * @set_ttbr0_cfg: Set the TTBR0 config for the GPUs context bank. A
|
| H A D | vga_switcheroo.h | 78 * Determining the id requires the handler, so GPUs are given their
82 * @VGA_SWITCHEROO_MAX_CLIENTS: currently no more than two GPUs are supported
|
| /linux/drivers/gpu/drm/v3d/ |
| H A D | Kconfig | 12 V3D 3.x or newer GPUs. SoCs supported include the BCM2711,
|
| /linux/drivers/gpu/drm/lima/ |
| H A D | Kconfig | 16 DRM driver for ARM Mali 400/450 GPUs.
|
| /linux/drivers/gpu/drm/ast/ |
| H A D | Kconfig | 14 is bound to the driver. These GPUs are commonly found
|
| /linux/drivers/gpu/drm/etnaviv/ |
| H A D | Kconfig | 16 DRM driver for Vivante GPUs.
|
| /linux/drivers/pci/ |
| H A D | Kconfig | 330 int "Maximum number of GPUs"
335 multiple GPUS. The overhead for each GPU is very small.
|
| /linux/drivers/platform/x86/ |
| H A D | apple-gmux.c | 31 * gmux is a microcontroller built into the MacBook Pro to support dual GPUs:
41 * dual GPUs but no built-in display.)
362 * On pre-retinas, the LVDS outputs of both GPUs feed into gmux which muxes
390 * combined DP/Thunderbolt port and lost the ability to switch it between GPUs,
415 * the integrated GPU, *both* GPUs will be in use for maximum performance.
|