162306a36Sopenharmony_ci# SPDX-License-Identifier: GPL-2.0-only 262306a36Sopenharmony_ci# 362306a36Sopenharmony_ci# Compute Acceleration device configuration 462306a36Sopenharmony_ci# 562306a36Sopenharmony_ci# This framework provides support for compute acceleration devices, such 662306a36Sopenharmony_ci# as, but not limited to, Machine-Learning and Deep-Learning acceleration 762306a36Sopenharmony_ci# devices 862306a36Sopenharmony_ci# 962306a36Sopenharmony_ciif DRM 1062306a36Sopenharmony_ci 1162306a36Sopenharmony_cimenuconfig DRM_ACCEL 1262306a36Sopenharmony_ci bool "Compute Acceleration Framework" 1362306a36Sopenharmony_ci help 1462306a36Sopenharmony_ci Framework for device drivers of compute acceleration devices, such 1562306a36Sopenharmony_ci as, but not limited to, Machine-Learning and Deep-Learning 1662306a36Sopenharmony_ci acceleration devices. 1762306a36Sopenharmony_ci If you say Y here, you need to select the module that's right for 1862306a36Sopenharmony_ci your acceleration device from the list below. 1962306a36Sopenharmony_ci This framework is integrated with the DRM subsystem as compute 2062306a36Sopenharmony_ci accelerators and GPUs share a lot in common and can use almost the 2162306a36Sopenharmony_ci same infrastructure code. 2262306a36Sopenharmony_ci Having said that, acceleration devices will have a different 2362306a36Sopenharmony_ci major number than GPUs, and will be exposed to user-space using 2462306a36Sopenharmony_ci different device files, called accel/accel* (in /dev, sysfs 2562306a36Sopenharmony_ci and debugfs). 2662306a36Sopenharmony_ci 2762306a36Sopenharmony_cisource "drivers/accel/habanalabs/Kconfig" 2862306a36Sopenharmony_cisource "drivers/accel/ivpu/Kconfig" 2962306a36Sopenharmony_cisource "drivers/accel/qaic/Kconfig" 3062306a36Sopenharmony_ci 3162306a36Sopenharmony_ciendif 32