commit: 840739d7f65e0bd1827fcc4500e386f25a461cc1
Author: Sv. Lockal <lockalsash <AT> gmail <DOT> com>
AuthorDate: Sun Dec 8 15:20:02 2024 +0000
Commit: Sam James <sam <AT> gentoo <DOT> org>
CommitDate: Sun Jan 5 21:46:33 2025 +0000
URL: https://gitweb.gentoo.org/repo/gentoo.git/commit/?id=840739d7
sci-libs/rocPRIM: add 6.3.0
Signed-off-by: Sv. Lockal <lockalsash <AT> gmail.com>
Signed-off-by: Sam James <sam <AT> gentoo.org>
sci-libs/rocPRIM/Manifest | 1 +
.../rocPRIM-6.3.0-expand-isa-compatibility.patch | 33 ++++++++++
.../files/rocPRIM-6.3.0-fix-clang-template.patch | 29 +++++++++
.../rocPRIM/files/rocPRIM-6.3.0-fix-libcxx.patch | 71 ++++++++++++++++++++++
sci-libs/rocPRIM/rocPRIM-6.3.0.ebuild | 70 +++++++++++++++++++++
5 files changed, 204 insertions(+)
diff --git a/sci-libs/rocPRIM/Manifest b/sci-libs/rocPRIM/Manifest
index cf2bbede484f..1851042b0e4e 100644
--- a/sci-libs/rocPRIM/Manifest
+++ b/sci-libs/rocPRIM/Manifest
@@ -1,3 +1,4 @@
DIST rocPRIM-5.1.3.tar.gz 374510 BLAKE2B
ab6960e7bd2159ac7a0d72ba6d594684f8d47028eca0940eabd35b346ac3d432a734ec575ee71341f339a9d0dead10dfafe81fb651a3b7da681aa900a5132d0e
SHA512
54e14f2b40795153b862a64c9b3d336f35feccfda725daad75fae356b0147c577735884b65218c26c370ebec710af0f84aeef3103067a50db077cf9e24d2b64a
DIST rocPRIM-5.7.1.tar.gz 535649 BLAKE2B
469bf59b5c92c37df96f58bac5a6559dc2cb879e5f82e539881d79bda57d23c25a9b114466042258e87862a88cd53d260155d7785c9a69a1800b0d05e931f56d
SHA512
b2f0bc07dbc5cd111dd513f6c05dbc533908c52ea99caf77d6a4dd35db2b28f98c80006bd1f50a232873eab00b70e54231c38bfd1035c8845029d53690fd5e71
DIST rocPRIM-6.1.1.tar.gz 611372 BLAKE2B
984df214179a6d2c90b31bd30ec9472a0b985d9d488ea195968f25df4cac97ce48bfa4c322f2d578771ac63caeafc2c69c9dae911bc3a9d920ab9558ba7d6e15
SHA512
298eebc8a5d3fd7da71ab98a22fd39183436b3d9e14945e450f0fb35e38ea8fb99c5f2b342f1f77f21899a14d506ce96a965fbdb24f106ec9638dcd6afe6ae98
+DIST rocPRIM-6.3.0.tar.gz 745936 BLAKE2B
1cdcf886c823959bbb03f53cb6e17abdb009fa48f8e00e96f8d962dd28ef9fb8b6ed796be079b0a3948adc832de8e3449d6439711db821b8a26c5cdc7122ce61
SHA512
c38f3cebfb32c0c9d4f9c1ad261c1dbe793dec1ebc92cf024ef32606f99c91e178526d77a24ad18792099e6f3aafcea43f7bc9282bbc144672684cd5fe296a8b
diff --git
a/sci-libs/rocPRIM/files/rocPRIM-6.3.0-expand-isa-compatibility.patch
b/sci-libs/rocPRIM/files/rocPRIM-6.3.0-expand-isa-compatibility.patch
new file mode 100644
index 000000000000..8a13924c1056
--- /dev/null
+++ b/sci-libs/rocPRIM/files/rocPRIM-6.3.0-expand-isa-compatibility.patch
@@ -0,0 +1,33 @@
+diff --git a/rocprim/include/rocprim/device/config_types.hpp
b/rocprim/include/rocprim/device/config_types.hpp
+index 58729b1..7e356da 100644
+--- a/rocprim/include/rocprim/device/config_types.hpp
++++ b/rocprim/include/rocprim/device/config_types.hpp
+@@ -204,16 +204,23 @@ constexpr bool prefix_equals(const char* lhs, const
char* rhs, std::size_t n)
+ constexpr target_arch get_target_arch_from_name(const char* const arch_name,
const std::size_t n)
+ {
+ constexpr const char* target_names[]
+- = {"gfx803", "gfx900", "gfx906", "gfx908", "gfx90a", "gfx1030",
"gfx1100", "gfx1102"};
++ = {"gfx803",
++ "gfx900", "gfx902", "gfx909", "gfx912",
++ "gfx906",
++ "gfx908",
++ "gfx90a",
++ "gfx1030", "gfx1031", "gfx1032", "gfx1033", "gfx1034", "gfx1035",
"gfx1036",
++ "gfx1100", "gfx1101",
++ "gfx1102", "gfx1103", "gfx1150", "gfx1151", "gfx1152", "gfx1153"};
+ constexpr target_arch target_architectures[] = {
+ target_arch::gfx803,
+- target_arch::gfx900,
++ target_arch::gfx900, target_arch::gfx900, target_arch::gfx900,
target_arch::gfx900,
+ target_arch::gfx906,
+ target_arch::gfx908,
+ target_arch::gfx90a,
+- target_arch::gfx1030,
+- target_arch::gfx1100,
+- target_arch::gfx1102,
++ target_arch::gfx1030, target_arch::gfx1030, target_arch::gfx1030,
target_arch::gfx1030, target_arch::gfx1030, target_arch::gfx1030,
target_arch::gfx1030,
++ target_arch::gfx1100, target_arch::gfx1100,
++ target_arch::gfx1102, target_arch::gfx1102, target_arch::gfx1102,
target_arch::gfx1102, target_arch::gfx1102, target_arch::gfx1102,
+ };
+ static_assert(sizeof(target_names) / sizeof(target_names[0])
+ == sizeof(target_architectures) /
sizeof(target_architectures[0]),
diff --git a/sci-libs/rocPRIM/files/rocPRIM-6.3.0-fix-clang-template.patch
b/sci-libs/rocPRIM/files/rocPRIM-6.3.0-fix-clang-template.patch
new file mode 100644
index 000000000000..089ce6187979
--- /dev/null
+++ b/sci-libs/rocPRIM/files/rocPRIM-6.3.0-fix-clang-template.patch
@@ -0,0 +1,29 @@
+Fix compilation with clang-19
+Backports
https://github.com/ROCm/rocPRIM/commit/c57b04baea872078bfb5b4af1165c7584fd3a95b
+--- a/rocprim/include/rocprim/device/detail/device_radix_sort.hpp
++++ b/rocprim/include/rocprim/device/detail/device_radix_sort.hpp
+@@ -526,15 +526,15 @@ ROCPRIM_DEVICE ROCPRIM_FORCE_INLINE void
sort_single(KeysInputIterator keys_i
+
+ ROCPRIM_SHARED_MEMORY typename sort_single_helper::storage_type storage;
+
+- sort_single_helper().template sort_single(keys_input,
+- keys_output,
+- values_input,
+- values_output,
+- size,
+- decomposer,
+- bit,
+- current_radix_bits,
+- storage);
++ sort_single_helper().template sort_single<>(keys_input,
++ keys_output,
++ values_input,
++ values_output,
++ size,
++ decomposer,
++ bit,
++ current_radix_bits,
++ storage);
+ }
+
+ template<class T>
diff --git a/sci-libs/rocPRIM/files/rocPRIM-6.3.0-fix-libcxx.patch
b/sci-libs/rocPRIM/files/rocPRIM-6.3.0-fix-libcxx.patch
new file mode 100644
index 000000000000..3827829483fb
--- /dev/null
+++ b/sci-libs/rocPRIM/files/rocPRIM-6.3.0-fix-libcxx.patch
@@ -0,0 +1,71 @@
+Fix ambiguous declarations for libc++, which treats __int128_t as integral.
+The issue was fixed in develop branch, but not in release.
+Upstream commit:
https://github.com/ROCm/rocPRIM/commit/81f6073790dee8d310e5b68cf46aae4b797cc059
+--- a/rocprim/include/rocprim/thread/radix_key_codec.hpp
++++ b/rocprim/include/rocprim/thread/radix_key_codec.hpp
+@@ -78,6 +78,7 @@ struct radix_key_codec_integral<Key,
+ }
+ };
+
++#ifndef _LIBCPP_VERSION
+ template<class Key, class BitKey>
+ struct radix_key_codec_integral<
+ Key,
+@@ -104,6 +105,7 @@ struct radix_key_codec_integral<
+ return static_cast<unsigned int>(bit_key >> start) & mask;
+ }
+ };
++#endif
+
+ template<class Key, class BitKey>
+ struct radix_key_codec_integral<Key,
+@@ -135,6 +137,7 @@ struct radix_key_codec_integral<Key,
+ }
+ };
+
++#ifndef _LIBCPP_VERSION
+ template<class Key, class BitKey>
+ struct radix_key_codec_integral<Key,
+ BitKey,
+@@ -164,6 +167,7 @@ struct radix_key_codec_integral<Key,
+ return static_cast<unsigned int>(bit_key >> start) & mask;
+ }
+ };
++#endif
+
+ template<class Key, class BitKey>
+ struct radix_key_codec_floating
+@@ -225,6 +229,7 @@ struct radix_key_codec_base<Key, typename
std::enable_if<::rocprim::is_integral<
+ : radix_key_codec_integral<Key, typename std::make_unsigned<Key>::type>
+ {};
+
++#ifndef _LIBCPP_VERSION
+ template<class Key>
+ struct radix_key_codec_base<Key,
+ typename std::enable_if<std::is_same<Key,
__int128_t>::value>::type>
+@@ -236,6 +241,7 @@ struct radix_key_codec_base<Key,
+ typename std::enable_if<std::is_same<Key,
__uint128_t>::value>::type>
+ : radix_key_codec_integral<Key, __uint128_t>
+ {};
++#endif
+
+ template<>
+ struct radix_key_codec_base<bool>
+--- a/test/rocprim/test_utils_data_generation.hpp
++++ b/test/rocprim/test_utils_data_generation.hpp
+@@ -268,6 +268,7 @@ inline OutputIter segmented_generate_n(OutputIter it,
size_t size, Generator&& g
+ return it + size;
+ }
+
++#ifndef _LIBCPP_VERSION
+ template<class OutputIter, class U, class V, class Generator>
+ inline auto generate_random_data_n(OutputIter it, size_t size, U min, V max,
Generator&& gen)
+ -> std::enable_if_t<std::is_same<it_value_t<OutputIter>,
__int128_t>::value, OutputIter>
+@@ -299,6 +300,7 @@ inline auto generate_random_data_n(OutputIter it, size_t
size, U min, V max, Gen
+
+ return segmented_generate_n(it, size, [&]() { return
static_cast<T>(distribution(gen)); });
+ }
++#endif
+
+ template<class OutputIter, class U, class V, class Generator>
+ inline auto generate_random_data_n(OutputIter it, size_t size, U min, V max,
Generator&& gen)
diff --git a/sci-libs/rocPRIM/rocPRIM-6.3.0.ebuild
b/sci-libs/rocPRIM/rocPRIM-6.3.0.ebuild
new file mode 100644
index 000000000000..cd561fb6b22d
--- /dev/null
+++ b/sci-libs/rocPRIM/rocPRIM-6.3.0.ebuild
@@ -0,0 +1,70 @@
+# Copyright 1999-2024 Gentoo Authors
+# Distributed under the terms of the GNU General Public License v2
+
+EAPI=8
+
+ROCM_VERSION=${PV}
+inherit cmake flag-o-matic rocm
+
+DESCRIPTION="HIP parallel primitives for developing performant GPU-accelerated
code on ROCm"
+HOMEPAGE="https://github.com/ROCm/rocPRIM";
+SRC_URI="https://github.com/ROCm/rocPRIM/archive/rocm-${PV}.tar.gz ->
rocPRIM-${PV}.tar.gz"
+S="${WORKDIR}/rocPRIM-rocm-${PV}"
+
+LICENSE="MIT"
+SLOT="0/$(ver_cut 1-2)"
+KEYWORDS="~amd64"
+IUSE="benchmark test"
+REQUIRED_USE="
+ benchmark? ( ${ROCM_REQUIRED_USE} )
+ test? ( ${ROCM_REQUIRED_USE} )
+"
+
+RDEPEND="dev-util/hip
+ benchmark? ( dev-cpp/benchmark )
+ test? ( dev-cpp/gtest )"
+BDEPEND="dev-build/rocm-cmake
+ >=dev-build/cmake-3.22"
+DEPEND="${RDEPEND}"
+
+RESTRICT="!test? ( test )"
+
+PATCHES=(
+ "${FILESDIR}"/${PN}-6.3.0-expand-isa-compatibility.patch
+ "${FILESDIR}"/${PN}-6.3.0-fix-clang-template.patch
+ "${FILESDIR}"/${PN}-6.3.0-fix-libcxx.patch
+)
+
+src_prepare() {
+ # install benchmark files
+ if use benchmark; then
+ sed -e
"/get_filename_component/s,\${BENCHMARK_SOURCE},${PN}_\${BENCHMARK_SOURCE}," \
+ -e "/add_executable/a\ install(TARGETS
\${BENCHMARK_TARGET})" -i benchmark/CMakeLists.txt || die
+ fi
+
+ cmake_src_prepare
+}
+
+src_configure() {
+ rocm_use_hipcc
+
+ # too many warnings in tests
+ append-cxxflags -Wno-explicit-specialization-storage-class
-Wno-deprecated-declarations
+
+ local mycmakeargs=(
+ -DCMAKE_SKIP_RPATH=ON
+ -DAMDGPU_TARGETS="$(get_amdgpu_flags)"
+ -DBUILD_TEST=$(usex test ON OFF)
+ -DBUILD_BENCHMARK=$(usex benchmark ON OFF)
+ -DBUILD_FILE_REORG_BACKWARD_COMPATIBILITY=OFF
+ -DROCM_SYMLINK_LIBS=OFF
+ )
+
+ cmake_src_configure
+}
+
+src_test() {
+ check_amdgpu
+ # uses HMM to fit tests to default <512M iGPU VRAM
+ ROCPRIM_USE_HMM="1" cmake_src_test -j1
+}
