[gentoo-dev] [PATCH v7 1/2] rocm.eclass: new eclass

[Yiyang Wu]

This eclass provides utilities for ROCm libraries in
https://github.com/ROCmSoftwarePlatform, e.g. rocBLAS, rocFFT.
It contains a USE_EXPAND, amdgpu_targets_*, which handles the GPU
architecture to compile, and keep targets coherent among dependencies.
Packages that depend on ROCm libraries, like cupy, can also make use of
this eclass, mainly specify GPU architecture and it's corresponding
dependencies via USE_EXPAND.

Closes: https://bugs.gentoo.org/810619
Bugs: https://bugs.gentoo.org/817440
Signed-off-by: Yiyang Wu <xgreenlandforwyy@×××××.com>
---
 eclass/rocm.eclass          | 223 ++++++++++++++++++++++++++++++++++++
 profiles/base/make.defaults |   2 +-
 2 files changed, 224 insertions(+), 1 deletion(-)
 create mode 100644 eclass/rocm.eclass

diff --git a/eclass/rocm.eclass b/eclass/rocm.eclass
new file mode 100644
index 000000000000..4c8fd39f2491
--- /dev/null
+++ b/eclass/rocm.eclass
@@ -0,0 +1,223 @@
+# Copyright 2022 Gentoo Authors
+# Distributed under the terms of the GNU General Public License v2
+
+# @ECLASS: rocm.eclass
+# @MAINTAINER:
+# Gentoo Science Project <sci@g.o>
+# @AUTHOR:
+# Yiyang Wu <xgreenlandforwyy@×××××.com>
+# @SUPPORTED_EAPIS: 7 8
+# @BLURB: Common functions and variables for ROCm packages written in HIP
+# @DESCRIPTION:
+# ROCm packages such as sci-libs/<roc|hip>*, and packages built on top of ROCm
+# libraries, can utilize variables and functions provided by this eclass.
+# It handles the AMDGPU_TARGETS variable via USE_EXPAND, so user can
+# edit USE flag to control which GPU architecture to compile. Using
+# ${ROCM_USEDEP} can ensure coherence among dependencies. Ebuilds can call the
+# function get_amdgpu_flag to translate activated target to GPU compile flags,
+# passing it to configuration. Function check_amdgpu can help ebuild ensure
+# read and write permissions to GPU device in src_test phase, throwing friendly
+# error message if unavailable.
+#
+# @EXAMPLE:
+# Example ebuild for ROCm library in https://github.com/ROCmSoftwarePlatform
+# which uses cmake to build and test, and depends on rocBLAS:
+# @CODE
+# ROCM_VERSION=${PV}
+# inherit cmake rocm
+# # ROCm libraries SRC_URI is usually in form of:
+# SRC_URI="https://github.com/ROCmSoftwarePlatform/${PN}/archive/rocm-${PV}.tar.gz -> ${P}.tar.gz"
+# S=${WORKDIR}/${PN}-rocm-${PV}
+# SLOT="0/$(ver_cut 1-2)"
+# IUSE="test"
+# REQUIRED_USE="${ROCM_REQUIRED_USE}"
+# RESTRICT="!test? ( test )"
+#
+# RDEPEND="
+#     dev-util/hip
+#     sci-libs/rocBLAS:${SLOT}[${ROCM_USEDEP}]
+# "
+#
+# src_configure() {
+#     # avoid sandbox violation
+#     addpredict /dev/kfd
+#     addpredict /dev/dri/
+#     local mycmakeargs=(
+#         -DAMDGPU_TARGETS="$(get_amdgpu_flags)"
+#         -DBUILD_CLIENTS_TESTS=$(usex test ON OFF)
+#     )
+#     CXX=hipcc cmake_src_configure
+# }
+#
+# src_test() {
+#     check_amdgpu
+#     # export LD_LIBRARY_PATH=<path to built lib dir> if necessary
+#     cmake_src_test # for packages using the cmake test
+#     # For packages using a standalone test binary rather than cmake test,
+#     # just execute it (or using edob)
+# }
+# @CODE
+#
+# Examples for packages depend on ROCm libraries -- a package which depends on
+# rocBLAS, uses comma separated ${HCC_AMDGPU_TARGET} to determine GPU
+# architectures, and requires ROCm version >=5.1
+# @CODE
+# ROCM_VERSION=5.1
+# inherit rocm
+# IUSE="rocm"
+# REQUIRED_USE="rocm? ( ${ROCM_REQUIRED_USE} )"
+# DEPEND="rocm? ( >=dev-util/hip-${ROCM_VERSION}
+#     >=sci-libs/rocBLAS-${ROCM_VERSION}[${ROCM_USEDEP}] )"
+#
+# src_configure() {
+#     if use rocm; then
+#         local amdgpu_flags=$(get_amdgpu_flags)
+#         export HCC_AMDGPU_TARGET=${amdgpu_flags//;/,}
+#     fi
+#     default
+# }
+# src_test() {
+#     use rocm && check_amdgpu
+#     default
+# }
+# @CODE
+
+if [[ ! ${_ROCM_ECLASS} ]]; then
+
+case ${EAPI} in
+	7|8) ;;
+	*) die "${ECLASS}: EAPI ${EAPI:-0} not supported" ;;
+esac
+
+# @ECLASS_VARIABLE: ROCM_VERSION
+# @REQUIRED
+# @PRE_INHERIT
+# @DESCRIPTION:
+# The ROCm version of current package. For ROCm libraries, it should be ${PV};
+# for other packages that depend on ROCm libraries, this can be set to match
+# the version required for ROCm libraries.
+
+# @ECLASS_VARIABLE: ROCM_REQUIRED_USE
+# @OUTPUT_VARIABLE
+# @DESCRIPTION:
+# Requires at least one AMDGPU target to be compiled.
+# Example use for ROCm libraries:
+# @CODE
+# REQUIRED_USE="${ROCM_REQUIRED_USE}"
+# @CODE
+# Example use for packages that depend on ROCm libraries:
+# @CODE
+# IUSE="rocm"
+# REQUIRED_USE="rocm? ( ${ROCM_REQUIRED_USE} )"
+# @CODE
+
+# @ECLASS_VARIABLE: ROCM_USEDEP
+# @OUTPUT_VARIABLE
+# @DESCRIPTION:
+# This is an eclass-generated USE-dependency string which can be used to
+# depend on another ROCm package being built for the same AMDGPU architecture.
+#
+# The generated USE-flag list is compatible with packages using rocm.eclass.
+#
+# Example use:
+# @CODE
+# DEPEND="sci-libs/rocBLAS[${ROCM_USEDEP}]"
+# @CODE
+
+# @FUNCTION: _rocm_set_globals
+# @DESCRIPTION:
+# Set global variables useful to ebuilds: IUSE, ROCM_REQUIRED_USE, and
+# ROCM_USEDEP
+_rocm_set_globals() {
+	# Two lists of AMDGPU_TARGETS of certain ROCm version.  Official support
+	# matrix:
+	# https://docs.amd.com/bundle/ROCm-Installation-Guide-v${ROCM_VERSION}/page/Prerequisite_Actions.html.
+	# There is no well-known unofficial support matrix.
+	# https://github.com/Bengt/ROCm/blob/patch-2/README.md#library-target-matrix
+	# may help. Gentoo have patches to enable gfx1031 as well.
+	local unofficial_amdgpu_targets official_amdgpu_targets
+	case ${ROCM_VERSION} in
+		4.*)
+			unofficial_amdgpu_targets=(
+				gfx803 gfx900 gfx1010 gfx1011 gfx1012 gfx1030
+			)
+			official_amdgpu_targets=(
+				gfx906 gfx908
+			)
+			;;
+		5.*)
+			unofficial_amdgpu_targets=(
+				gfx803 gfx900 gfx1010 gfx1011 gfx1012 gfx1031
+			)
+			official_amdgpu_targets=(
+				gfx906 gfx908 gfx90a gfx1030
+			)
+			;;
+		*)
+			die "Unknown ROCm major version! Please update rocm.eclass before bumping to new ebuilds"
+			;;
+	esac
+
+	local iuse_flags=(
+		"${official_amdgpu_targets[@]/#/+amdgpu_targets_}"
+		"${unofficial_amdgpu_targets[@]/#/amdgpu_targets_}"
+	)
+	IUSE="${iuse_flags[*]}"
+
+	local all_amdgpu_targets=(
+		"${official_amdgpu_targets[@]}"
+		"${unofficial_amdgpu_targets[@]}"
+	)
+	local allflags=( "${all_amdgpu_targets[@]/#/amdgpu_targets_}" )
+	ROCM_REQUIRED_USE=" || ( ${allflags[*]} )"
+
+	local optflags=${allflags[@]/%/(-)?}
+	ROCM_USEDEP=${optflags// /,}
+}
+_rocm_set_globals
+unset -f _rocm_set_globals
+
+
+# @FUNCTION: get_amdgpu_flags
+# @USAGE: get_amdgpu_flags
+# @DESCRIPTION:
+# Convert specified use flag of amdgpu_targets to compilation flags.
+# Append default target feature to GPU arch. See
+# https://llvm.org/docs/AMDGPUUsage.html#target-features
+get_amdgpu_flags() {
+	local amdgpu_target_flags
+	for gpu_target in ${AMDGPU_TARGETS}; do
+	local target_feature=
+		case ${gpu_target} in
+			gfx906|gfx908)
+				target_feature=:xnack-
+				;;
+			gfx90a)
+				target_feature=:xnack+
+				;;
+			*)
+				;;
+		esac
+		amdgpu_target_flags+="${gpu_target}${target_feature};"
+	done
+	echo "${amdgpu_target_flags}"
+}
+
+# @FUNCTION: check_amdgpu
+# @USAGE: check_amdgpu
+# @DESCRIPTION:
+# grant and check read-write permissions on AMDGPU devices, die if not available.
+check_amdgpu() {
+	for device in /dev/kfd /dev/dri/render*; do
+		addwrite ${device}
+		if [[ ! -r ${device} || ! -w ${device} ]]; then
+			eerror "Cannot read or write ${device}!"
+			eerror "Make sure it is present and check the permission."
+			ewarn "By default render group have access to it. Check if portage user is in render group."
+			die "${device} inaccessible"
+		fi
+	done
+}
+
+_ROCM_ECLASS=1
+fi
diff --git a/profiles/base/make.defaults b/profiles/base/make.defaults
index 326cb28de537..2c288d12d103 100644
--- a/profiles/base/make.defaults
+++ b/profiles/base/make.defaults
@@ -13,7 +13,7 @@ USE_EXPAND_VALUES_USERLAND="BSD GNU"
 
 # Env vars to expand into USE vars.  Modifying this requires prior
 # discussion on gentoo-dev@l.g.o.
-USE_EXPAND="ABI_MIPS ABI_S390 ABI_X86 ADA_TARGET ALSA_CARDS APACHE2_MODULES APACHE2_MPMS CALLIGRA_FEATURES CAMERAS COLLECTD_PLUGINS CPU_FLAGS_ARM CPU_FLAGS_PPC CPU_FLAGS_X86 CURL_SSL ELIBC FFTOOLS GPSD_PROTOCOLS GRUB_PLATFORMS INPUT_DEVICES KERNEL L10N LCD_DEVICES LIBREOFFICE_EXTENSIONS LLVM_TARGETS LUA_SINGLE_TARGET LUA_TARGETS MONKEYD_PLUGINS NGINX_MODULES_HTTP NGINX_MODULES_MAIL NGINX_MODULES_STREAM OFFICE_IMPLEMENTATION OPENMPI_FABRICS OPENMPI_OFED_FEATURES OPENMPI_RM PHP_TARGETS POSTGRES_TARGETS PYTHON_SINGLE_TARGET PYTHON_TARGETS QEMU_SOFTMMU_TARGETS QEMU_USER_TARGETS ROS_MESSAGES RUBY_TARGETS SANE_BACKENDS USERLAND UWSGI_PLUGINS VIDEO_CARDS VOICEMAIL_STORAGE XTABLES_ADDONS"
+USE_EXPAND="ABI_MIPS ABI_S390 ABI_X86 ADA_TARGET ALSA_CARDS AMDGPU_TARGETS APACHE2_MODULES APACHE2_MPMS CALLIGRA_FEATURES CAMERAS COLLECTD_PLUGINS CPU_FLAGS_ARM CPU_FLAGS_PPC CPU_FLAGS_X86 CURL_SSL ELIBC FFTOOLS GPSD_PROTOCOLS GRUB_PLATFORMS INPUT_DEVICES KERNEL L10N LCD_DEVICES LIBREOFFICE_EXTENSIONS LLVM_TARGETS LUA_SINGLE_TARGET LUA_TARGETS MONKEYD_PLUGINS NGINX_MODULES_HTTP NGINX_MODULES_MAIL NGINX_MODULES_STREAM OFFICE_IMPLEMENTATION OPENMPI_FABRICS OPENMPI_OFED_FEATURES OPENMPI_RM PHP_TARGETS POSTGRES_TARGETS PYTHON_SINGLE_TARGET PYTHON_TARGETS QEMU_SOFTMMU_TARGETS QEMU_USER_TARGETS ROS_MESSAGES RUBY_TARGETS SANE_BACKENDS USERLAND UWSGI_PLUGINS VIDEO_CARDS VOICEMAIL_STORAGE XTABLES_ADDONS"
 
 # USE_EXPAND variables whose contents are not shown in package manager
 # output. Changes need discussion on gentoo-dev.
-- 
2.34.1