| 1 | # SPDX-License-Identifier: GPL-2.0-only |
| 2 | # |
| 3 | # Compute Acceleration device configuration |
| 4 | # |
| 5 | # This framework provides support for compute acceleration devices, such |
| 6 | # as, but not limited to, Machine-Learning and Deep-Learning acceleration |
| 7 | # devices |
| 8 | # |
| 9 | if DRM |
| 10 | |
| 11 | menuconfig DRM_ACCEL |
| 12 | bool "Compute Acceleration Framework" |
| 13 | help |
| 14 | Framework for device drivers of compute acceleration devices, such |
| 15 | as, but not limited to, Machine-Learning and Deep-Learning |
| 16 | acceleration devices. |
| 17 | If you say Y here, you need to select the module that's right for |
| 18 | your acceleration device from the list below. |
| 19 | This framework is integrated with the DRM subsystem as compute |
| 20 | accelerators and GPUs share a lot in common and can use almost the |
| 21 | same infrastructure code. |
| 22 | Having said that, acceleration devices will have a different |
| 23 | major number than GPUs, and will be exposed to user-space using |
| 24 | different device files, called accel/accel* (in /dev, sysfs |
| 25 | and debugfs). |
| 26 | |
| 27 | source "drivers/accel/amdxdna/Kconfig" |
| 28 | source "drivers/accel/ethosu/Kconfig" |
| 29 | source "drivers/accel/habanalabs/Kconfig" |
| 30 | source "drivers/accel/ivpu/Kconfig" |
| 31 | source "drivers/accel/qaic/Kconfig" |
| 32 | source "drivers/accel/rocket/Kconfig" |
| 33 | |
| 34 | endif |