git: 4fd08b5074ce - main - biology/mmseqs2: Update to 16.747.c6
- Go to: [ bottom of page ] [ top of archives ] [ this month ]
Date: Wed, 15 Jan 2025 15:07:23 UTC
The branch main has been updated by jwb: URL: https://cgit.FreeBSD.org/ports/commit/?id=4fd08b5074ce3a5d4997f2837d86b406bcfb4cea commit 4fd08b5074ce3a5d4997f2837d86b406bcfb4cea Author: Jason W. Bacon <jwb@FreeBSD.org> AuthorDate: 2025-01-15 15:06:03 +0000 Commit: Jason W. Bacon <jwb@FreeBSD.org> CommitDate: 2025-01-15 15:06:03 +0000 biology/mmseqs2: Update to 16.747.c6 Numerous fixes and improvements since v13 Changes: https://github.com/soedinglab/MMseqs2/releases PR: 283251 Reported by: alster@vinterdalen.se --- biology/mmseqs2/Makefile | 11 ++--- biology/mmseqs2/distinfo | 6 +-- biology/mmseqs2/files/patch-CMakeLists.txt | 51 +++++++++++----------- .../files/patch-data_workflow_createtaxdb.sh | 12 ++--- .../mmseqs2/files/patch-data_workflow_databases.sh | 12 ++--- .../mmseqs2/files/patch-src_commons_DBReader.cpp | 11 ----- biology/mmseqs2/pkg-descr | 12 ++--- 7 files changed, 50 insertions(+), 65 deletions(-) diff --git a/biology/mmseqs2/Makefile b/biology/mmseqs2/Makefile index 0595f54412d7..c2c410252fd0 100644 --- a/biology/mmseqs2/Makefile +++ b/biology/mmseqs2/Makefile @@ -1,11 +1,10 @@ PORTNAME= MMseqs2 -DISTVERSION= 13-45111 -PORTREVISION= 2 +DISTVERSION= 16-747c6 CATEGORIES= biology MAINTAINER= jwb@FreeBSD.org COMMENT= Ultra fast and sensitive sequence search and clustering suite -WWW= https://github.com/soedinglab/MMseqs2 +WWW= https://github.com/soedinglab/MMseqs2/ LICENSE= GPLv3 LICENSE_FILE= ${WRKSRC}/LICENSE.md @@ -18,10 +17,12 @@ USES= cmake perl5 shebangfix USE_GITHUB= yes USE_PERL5= build -SHEBANG_GLOB= *.sh GH_ACCOUNT= soedinglab +SHEBANG_GLOB= *.sh + +CMAKE_ARGS+= -DVERSION_OVERRIDE=${DISTVERSION} +CMAKE_ON= DISABLE_IPS4O USE_SYSTEM_ZSTD -CMAKE_ARGS+= -DUSE_SYSTEM_ZSTD:BOOL=ON -DDISABLE_IPS4O:BOOL=ON LDFLAGS+= -lpthread PLIST_FILES= bin/mmseqs ${DATADIR}/bash-completion.sh diff --git a/biology/mmseqs2/distinfo b/biology/mmseqs2/distinfo index e29d9fdcbf95..2cef8860912b 100644 --- a/biology/mmseqs2/distinfo +++ b/biology/mmseqs2/distinfo @@ -1,3 +1,3 @@ -TIMESTAMP = 1624667730 -SHA256 (soedinglab-MMseqs2-13-45111_GH0.tar.gz) = 6444bb682ebf5ced54b2eda7a301fa3e933c2a28b7661f96ef5bdab1d53695a2 -SIZE (soedinglab-MMseqs2-13-45111_GH0.tar.gz) = 10196433 +TIMESTAMP = 1733910529 +SHA256 (soedinglab-MMseqs2-16-747c6_GH0.tar.gz) = faeb6841feb8e028651c2391de1346c55c2091a96520b625525d27b99d07ef1d +SIZE (soedinglab-MMseqs2-16-747c6_GH0.tar.gz) = 13359879 diff --git a/biology/mmseqs2/files/patch-CMakeLists.txt b/biology/mmseqs2/files/patch-CMakeLists.txt index 908984972649..743bc16ff5c4 100644 --- a/biology/mmseqs2/files/patch-CMakeLists.txt +++ b/biology/mmseqs2/files/patch-CMakeLists.txt @@ -1,6 +1,6 @@ ---- CMakeLists.txt.orig 2021-06-24 14:37:49 UTC +--- CMakeLists.txt.orig 2024-11-26 05:22:36 UTC +++ CMakeLists.txt -@@ -50,30 +50,19 @@ set(MMSEQS_CXX_FLAGS "-fsigned-char") +@@ -57,30 +57,19 @@ if (HAVE_AVX2) # SIMD instruction sets support set(MMSEQS_ARCH "") if (HAVE_AVX2) @@ -9,45 +9,44 @@ - else () - set(MMSEQS_ARCH "${MMSEQS_ARCH} -mavx2 -mcx16 -Wa,-q") - endif () - set(X64 1) + set(X64 1 CACHE INTERNAL "") elseif (HAVE_SSE4_1) - set(MMSEQS_ARCH "${MMSEQS_ARCH} -msse4.1 -mcx16") - set(X64 1) + set(X64 1 CACHE INTERNAL "") elseif (HAVE_SSE2) - set(MMSEQS_ARCH "${MMSEQS_ARCH} -msse2") set(DISABLE_IPS4O 1) - set(X64 1) + set(X64 1 CACHE INTERNAL "") elseif (HAVE_POWER9) - set(MMSEQS_ARCH "${MMSEQS_ARCH} -mcpu=power9 -mvsx") - set(PPC64 1) + set(PPC64 1 CACHE INTERNAL "") elseif (HAVE_POWER8) - set(MMSEQS_ARCH "${MMSEQS_ARCH} -mcpu=power8 -mvsx") - set(PPC64 1) + set(PPC64 1 CACHE INTERNAL "") elseif (HAVE_ARM8) - set(MMSEQS_ARCH "${MMSEQS_ARCH} -march=armv8-a+simd") - set(ARM 1) + set(ARM 1 CACHE INTERNAL "") elseif (HAVE_S390X) -- set(MMSEQS_ARCH "${MMSEQS_ARCH} -mzarch -march=z14") - set(ZARCH 1) +- set(MMSEQS_ARCH "${MMSEQS_ARCH} -march=z14 -mzarch -mzvector") + set(ZARCH 1 CACHE INTERNAL "") endif () -@@ -105,19 +94,6 @@ if (NATIVE_ARCH AND (MMSEQS_ARCH STREQUAL "")) +@@ -110,18 +99,6 @@ if (NATIVE_ARCH AND (MMSEQS_ARCH STREQUAL "")) + endif () + message(WARNING "At least SSE4.1 is needed for best performance") endif () - if (PPC64) - set(MMSEQS_ARCH "-mcpu=native") -- else () -- # clang has a problem with march=native on travis -- if (CMAKE_CXX_COMPILER_ID MATCHES "Clang" AND CMAKE_CXX_COMPILER_VERSION VERSION_LESS "4.0.0") -- set(MMSEQS_ARCH "${SSE_FLAGS}") -- else() -- set(MMSEQS_ARCH "-march=native") -- endif() -- endif () -- else () -- if (PPC64) -- set(MMSEQS_ARCH "-mcpu=native") -- else () +- # clang has a problem with march=native on travis +- if (CMAKE_CXX_COMPILER_ID MATCHES "Clang" AND CMAKE_CXX_COMPILER_VERSION VERSION_LESS "4.0.0") +- set(MMSEQS_ARCH "${SSE_FLAGS}") +- else() - set(MMSEQS_ARCH "-march=native") - endif () +- endif() +- elseif (PPC64 OR ARM) +- set(MMSEQS_ARCH "-mcpu=native") +- elseif (ZARCH) +- set(MMSEQS_ARCH "-mcpu=native -mzvector") +- else () +- set(MMSEQS_ARCH "-march=native") endif () endif () + set(MMSEQS_ARCH ${MMSEQS_ARCH} CACHE INTERNAL "") diff --git a/biology/mmseqs2/files/patch-data_workflow_createtaxdb.sh b/biology/mmseqs2/files/patch-data_workflow_createtaxdb.sh index 762b7a1addc2..efa7ec4374ba 100644 --- a/biology/mmseqs2/files/patch-data_workflow_createtaxdb.sh +++ b/biology/mmseqs2/files/patch-data_workflow_createtaxdb.sh @@ -1,6 +1,6 @@ ---- data/workflow/createtaxdb.sh.orig 2021-06-25 01:33:07 UTC +--- data/workflow/createtaxdb.sh.orig 2024-12-11 10:27:07 UTC +++ data/workflow/createtaxdb.sh -@@ -27,6 +27,8 @@ STRATEGY="" +@@ -27,6 +27,8 @@ if hasCommand wget; then STRATEGY="$STRATEGY WGET"; if hasCommand aria2c; then STRATEGY="$STRATEGY ARIA"; fi if hasCommand curl; then STRATEGY="$STRATEGY CURL"; fi if hasCommand wget; then STRATEGY="$STRATEGY WGET"; fi @@ -9,10 +9,10 @@ if [ "$STRATEGY" = "" ]; then fail "No download tool found in PATH. Please install aria2c, curl or wget." fi -@@ -47,6 +49,9 @@ downloadFile() { - ;; - WGET) - wget -O "$OUTPUT" "$URL" && return 0 +@@ -56,6 +58,9 @@ downloadFile() { + mv -f -- "${OUTPUT}.wget" "${OUTPUT}" + return 0 + fi + ;; + FETCH) + fetch -o "$OUTPUT" "$URL" && return 0 diff --git a/biology/mmseqs2/files/patch-data_workflow_databases.sh b/biology/mmseqs2/files/patch-data_workflow_databases.sh index 2b0a30427958..2a8168b4dd5e 100644 --- a/biology/mmseqs2/files/patch-data_workflow_databases.sh +++ b/biology/mmseqs2/files/patch-data_workflow_databases.sh @@ -1,6 +1,6 @@ ---- data/workflow/databases.sh.orig 2021-06-25 01:34:08 UTC +--- data/workflow/databases.sh.orig 2024-12-11 10:31:20 UTC +++ data/workflow/databases.sh -@@ -27,6 +27,8 @@ STRATEGY="" +@@ -27,6 +27,8 @@ if hasCommand wget; then STRATEGY="$STRATEGY WGET"; if hasCommand aria2c; then STRATEGY="$STRATEGY ARIA"; fi if hasCommand curl; then STRATEGY="$STRATEGY CURL"; fi if hasCommand wget; then STRATEGY="$STRATEGY WGET"; fi @@ -9,10 +9,10 @@ if [ "$STRATEGY" = "" ]; then fail "No download tool found in PATH. Please install aria2c, curl or wget." fi -@@ -47,6 +49,9 @@ downloadFile() { - ;; - WGET) - wget -O "$OUTPUT" "$URL" && return 0 +@@ -56,6 +58,9 @@ downloadFile() { + mv -f -- "${OUTPUT}.wget" "${OUTPUT}" + return 0 + fi + ;; + FETCH) + fetch -o "$OUTPUT" "$URL" && return 0 diff --git a/biology/mmseqs2/files/patch-src_commons_DBReader.cpp b/biology/mmseqs2/files/patch-src_commons_DBReader.cpp deleted file mode 100644 index 212b3e2ecf59..000000000000 --- a/biology/mmseqs2/files/patch-src_commons_DBReader.cpp +++ /dev/null @@ -1,11 +0,0 @@ ---- src/commons/DBReader.cpp.orig 2021-06-25 22:40:36 UTC -+++ src/commons/DBReader.cpp -@@ -1004,7 +1004,7 @@ void DBReader<T>::setSequentialAdvice() { - #ifdef HAVE_POSIX_MADVISE - for(size_t i = 0; i < dataFileCnt; i++){ - size_t dataSize = dataSizeOffset[i+1] - dataSizeOffset[i]; -- if (posix_madvise (dataFiles[i], dataSize, POSIX_MADV_SEQUENTIAL) != 0){ -+ if (dataSize > 0 && posix_madvise (dataFiles[i], dataSize, POSIX_MADV_SEQUENTIAL) != 0){ - Debug(Debug::ERROR) << "posix_madvise returned an error " << dataFileName << "\n"; - } - } diff --git a/biology/mmseqs2/pkg-descr b/biology/mmseqs2/pkg-descr index 9c359124e272..3665255fbf6e 100644 --- a/biology/mmseqs2/pkg-descr +++ b/biology/mmseqs2/pkg-descr @@ -1,8 +1,4 @@ -MMseqs2 (Many-against-Many sequence searching) is a software suite to search -and cluster huge protein and nucleotide sequence sets. MMseqs2 is open source -GPL-licensed software implemented in C++ for Linux, MacOS, and (as beta -version, via cygwin) Windows. The software is designed to run on multiple cores -and servers and exhibits very good scalability. MMseqs2 can run 10000 times -faster than BLAST. At 100 times its speed it achieves almost the same -sensitivity. It can perform profile searches with the same sensitivity as -PSI-BLAST at over 400 times its speed. +MMseqs2 (Many-against-Many searching) is a software suite to search +and cluster huge sequence sets. MMseqs2 is designed to run on multiple +cores and servers, making it highly scalable. MMseqs2 matches the +sensitivity of BLAST, but runs orders of magnitude faster.