[WIP] Update LAPACK to 3.9.0 (#2353)

* Update make.inc entries for LAPACK 3.9.0

Reference-LAPACK PR 347 changed some variable names and relative paths

* Update LAPACK to 3.9.0

* Add new functions from LAPACK 3.9.0

* Add new functions from LAPACK 3.9.0

* Restore LOADER command 

as it makes it easier to specify pthread as needed

* Restore LOADER

* Restore EIG/LIN prefixes in cmdbase

* add binary path to lapack_testing.py call

* Restore OpenMP version check

* Restore OpenMP version check

* Restore fix for out-of-bounds array accesses

from #2096

Author: martin-frbg

Makefile

@@ -247,21 +247,21 @@ prof_lapack : lapack_prebuild
 
 lapack_prebuild :
 ifeq ($(NOFORTRAN), $(filter 0,$(NOFORTRAN)))
-	-@echo "FORTRAN     = $(FC)" > $(NETLIB_LAPACK_DIR)/make.inc
-	-@echo "OPTS        = $(LAPACK_FFLAGS)" >> $(NETLIB_LAPACK_DIR)/make.inc
+	-@echo "FC          = $(FC)" > $(NETLIB_LAPACK_DIR)/make.inc
+	-@echo "FFLAGS      = $(LAPACK_FFLAGS)" >> $(NETLIB_LAPACK_DIR)/make.inc
 	-@echo "POPTS       = $(LAPACK_FPFLAGS)" >> $(NETLIB_LAPACK_DIR)/make.inc
-	-@echo "NOOPT       = -O0 $(LAPACK_NOOPT)" >> $(NETLIB_LAPACK_DIR)/make.inc
+	-@echo "FFLAGS_NOOPT       = -O0 $(LAPACK_NOOPT)" >> $(NETLIB_LAPACK_DIR)/make.inc
 	-@echo "PNOOPT      = $(LAPACK_FPFLAGS) -O0" >> $(NETLIB_LAPACK_DIR)/make.inc
-	-@echo "LOADOPTS    = $(FFLAGS) $(EXTRALIB)" >> $(NETLIB_LAPACK_DIR)/make.inc
+	-@echo "LDFLAGS     = $(FFLAGS) $(EXTRALIB)" >> $(NETLIB_LAPACK_DIR)/make.inc
 	-@echo "CC          = $(CC)" >> $(NETLIB_LAPACK_DIR)/make.inc
 	-@echo "override CFLAGS      = $(LAPACK_CFLAGS)" >> $(NETLIB_LAPACK_DIR)/make.inc
-	-@echo "override ARCH        = $(AR)" >> $(NETLIB_LAPACK_DIR)/make.inc
-	-@echo "ARCHFLAGS   = $(ARFLAGS) -ru" >> $(NETLIB_LAPACK_DIR)/make.inc
+	-@echo "AR          = $(AR)" >> $(NETLIB_LAPACK_DIR)/make.inc
+	-@echo "ARFLAGS     = $(ARFLAGS) -ru" >> $(NETLIB_LAPACK_DIR)/make.inc
 	-@echo "RANLIB      = $(RANLIB)" >> $(NETLIB_LAPACK_DIR)/make.inc
-	-@echo "LAPACKLIB   = ../$(LIBNAME)" >> $(NETLIB_LAPACK_DIR)/make.inc
-	-@echo "TMGLIB      = ../$(LIBNAME)" >> $(NETLIB_LAPACK_DIR)/make.inc
+	-@echo "LAPACKLIB   = ../../$(LIBNAME)" >> $(NETLIB_LAPACK_DIR)/make.inc
+	-@echo "TMGLIB      = ../../../$(LIBNAME)" >> $(NETLIB_LAPACK_DIR)/make.inc
 	-@echo "BLASLIB     = ../../../$(LIBNAME)" >> $(NETLIB_LAPACK_DIR)/make.inc
-	-@echo "LAPACKELIB  = ../$(LIBNAME)" >> $(NETLIB_LAPACK_DIR)/make.inc
+	-@echo "LAPACKELIB  = ../../../$(LIBNAME)" >> $(NETLIB_LAPACK_DIR)/make.inc
 	-@echo "LAPACKLIB_P = ../$(LIBNAME_P)" >> $(NETLIB_LAPACK_DIR)/make.inc
 	-@echo "SUFFIX      = $(SUFFIX)" >> $(NETLIB_LAPACK_DIR)/make.inc
 	-@echo "PSUFFIX     = $(PSUFFIX)" >> $(NETLIB_LAPACK_DIR)/make.inc
@@ -319,7 +319,7 @@ lapack-test :
 ifneq ($(CROSS), 1)
 	( cd $(NETLIB_LAPACK_DIR)/INSTALL; make all; ./testlsame; ./testslamch; ./testdlamch; \
         ./testsecond; ./testdsecnd; ./testieee; ./testversion )
-	(cd $(NETLIB_LAPACK_DIR); ./lapack_testing.py -r )
+	(cd $(NETLIB_LAPACK_DIR); ./lapack_testing.py -r -b TESTING)
 endif
 
 lapack-runtest:

cmake/lapack.cmake

@@ -115,7 +115,9 @@ set(SLASRC
    stplqt.f stplqt2.f stpmlqt.f
    ssytrd_2stage.f ssytrd_sy2sb.f ssytrd_sb2st.F ssb2st_kernels.f
    ssyevd_2stage.f ssyev_2stage.f ssyevx_2stage.f ssyevr_2stage.f
-   ssbev_2stage.f ssbevx_2stage.f ssbevd_2stage.f ssygv_2stage.f)
+   ssbev_2stage.f ssbevx_2stage.f ssbevd_2stage.f ssygv_2stage.f
+   scombssq.f sgesvdq.f slaorhr_col_getrfnp.f
+   slaorhr_col_getrfnp2.f sorgtsqr.f sorhr_col.f )
 
 set(SXLASRC sgesvxx.f sgerfsx.f sla_gerfsx_extended.f sla_geamv.f
    sla_gercond.f sla_gerpvgrw.f ssysvxx.f ssyrfsx.f
@@ -210,7 +212,9 @@ set(CLASRC
    ctplqt.f ctplqt2.f ctpmlqt.f
    chetrd_2stage.f chetrd_he2hb.f chetrd_hb2st.F chb2st_kernels.f
    cheevd_2stage.f cheev_2stage.f cheevx_2stage.f cheevr_2stage.f
-   chbev_2stage.f chbevx_2stage.f chbevd_2stage.f chegv_2stage.f)
+   chbev_2stage.f chbevx_2stage.f chbevd_2stage.f chegv_2stage.f
+   cgesvdq.f claunhr_col_getrfnp.f claunhr_col_getrfnp2.f 
+   cungtsqr.f cunhr_col.f )
 
 set(CXLASRC cgesvxx.f cgerfsx.f cla_gerfsx_extended.f cla_geamv.f
    cla_gercond_c.f cla_gercond_x.f cla_gerpvgrw.f
@@ -299,7 +303,9 @@ set(DLASRC
    dtplqt.f dtplqt2.f dtpmlqt.f
    dsytrd_2stage.f dsytrd_sy2sb.f dsytrd_sb2st.F dsb2st_kernels.f
    dsyevd_2stage.f dsyev_2stage.f dsyevx_2stage.f dsyevr_2stage.f
-   dsbev_2stage.f dsbevx_2stage.f dsbevd_2stage.f dsygv_2stage.f)
+   dsbev_2stage.f dsbevx_2stage.f dsbevd_2stage.f dsygv_2stage.f
+   dcombssq.f dgesvdq.f dlaorhr_col_getrfnp.f
+   dlaorhr_col_getrfnp2.f dorgtsqr.f dorhr_col.f )
 
 set(DXLASRC dgesvxx.f dgerfsx.f dla_gerfsx_extended.f dla_geamv.f
    dla_gercond.f dla_gerpvgrw.f dsysvxx.f dsyrfsx.f
@@ -398,7 +404,9 @@ set(ZLASRC
    zgelq.f zlaswlq.f zlamswlq.f zgemlq.f
    zhetrd_2stage.f zhetrd_he2hb.f zhetrd_hb2st.F zhb2st_kernels.f
    zheevd_2stage.f zheev_2stage.f zheevx_2stage.f zheevr_2stage.f
-   zhbev_2stage.f zhbevx_2stage.f zhbevd_2stage.f zhegv_2stage.f)
+   zhbev_2stage.f zhbevx_2stage.f zhbevd_2stage.f zhegv_2stage.f
+   zgesvdq.f zlaunhr_col_getrfnp.f zlaunhr_col_getrfnp2.f
+   zungtsqr.f zunhr_col.f)
 
 set(ZXLASRC zgesvxx.f zgerfsx.f zla_gerfsx_extended.f zla_geamv.f
    zla_gercond_c.f zla_gercond_x.f zla_gerpvgrw.f zsysvxx.f zsyrfsx.f

cmake/lapacke.cmake

@@ -715,6 +715,8 @@ set(DSRC
   lapacke_dgesv_work.c
   lapacke_dgesvd.c
   lapacke_dgesvd_work.c
+  lapacke_dgesvdq.c
+  lapacke_dgesvdq_work.c
   lapacke_dgesvdx.c
   lapacke_dgesvdx_work.c
   lapacke_dgesvj.c
@@ -1287,6 +1289,8 @@ set(SSRC
   lapacke_sgesv_work.c
   lapacke_sgesvd.c
   lapacke_sgesvd_work.c
+  lapacke_sgesvdq.c
+  lapacke_sgesvdq_work.c
   lapacke_sgesvdx.c
   lapacke_sgesvdx_work.c
   lapacke_sgesvj.c
@@ -1853,6 +1857,8 @@ set(ZSRC
   lapacke_zgesv_work.c
   lapacke_zgesvd.c
   lapacke_zgesvd_work.c
+  lapacke_zgesvdq.c
+  lapacke_zgesvdq_work.c
   lapacke_zgesvdx.c
   lapacke_zgesvdx_work.c
   lapacke_zgesvj.c

exports/gensymbol

@@ -694,7 +694,19 @@
 
     # functions added for lapack-3.8.0
 
-    ilaenv2stage
+    ilaenv2stage,
+
+    # functions added for lapack-3.9.0
+    cgesvdq,
+    cungtsqr,
+    dcombssq,
+    dgesvdq,
+    dorgtsqr,
+    scombssq,
+    sgesvdq,
+    sorgtsqr,
+    zgesvdq,
+    zungtsqr
 );
 
 @lapack_extendedprecision_objs = (
@@ -3347,6 +3359,15 @@
     LAPACKE_zsytrf_aa_2stage_work,
     LAPACKE_zsytrs_aa_2stage,
     LAPACKE_zsytrs_aa_2stage_work,
+    
+    # new functions from 3.9.0
+    LAPACKE_dgesvdq,
+    LAPACKE_dgesvdq_work,
+    LAPACKE_sgesvdq,
+    LAPACKE_sgesvdq_work,
+    LAPACKE_zgesvdq,
+    LAPACKE_zgesvdq_work
+
 );
 
 #These function may need 2 underscores.
@@ -3419,7 +3440,13 @@
     dsytrf_aa_2stage, dsytrs_aa_2stage,
     zhesv_aa_2stage, zhetrf_aa_2stage,
     zhetrs_aa_2stage, zsysv_aa_2stage,
-    zsytrf_aa_2stage, zsytrs_aa_2stage
+    zsytrf_aa_2stage, zsytrs_aa_2stage,
+# 3.9.0
+    claunhr_col_getrfnp, claunhr_col_getrfnp2, cunhr_col,
+    dlaorhr_col_getrfnp, dlaorhr_col_getrfnp2, dorhr_col,
+    slaorhr_col_getrfnp, slaorhr_col_getrfnp2, sorhr_col,
+    zlaunhr_col_getrfnp, zlaunhr_col_getrfnp2, zunhr_col
+
 );
 
 

lapack-netlib/.appveyor.yml

@@ -0,0 +1,38 @@
+image:
+- Visual Studio 2017
+
+configuration: Release
+clone_depth: 3
+
+matrix:
+  fast_finish: false
+
+skip_commits:
+# Add [av skip] to commit messages
+  message: /\[av skip\]/
+
+cache:
+  - '%APPVEYOR_BUILD_FOLDER%\build'
+
+environment:
+  global:
+    CONDA_INSTALL_LOCN: C:\\Miniconda36-x64
+
+install:
+  - call %CONDA_INSTALL_LOCN%\Scripts\activate.bat
+  - conda config --add channels conda-forge --force
+  - conda install --yes --quiet flang jom
+  - call "C:\Program Files (x86)\Microsoft Visual Studio 14.0\VC\vcvarsall.bat" amd64
+  - set "LIB=%CONDA_INSTALL_LOCN%\Library\lib;%LIB%"
+  - set "CPATH=%CONDA_INSTALL_LOCN%\Library\include;%CPATH%"
+
+before_build:
+  - ps: if (-Not (Test-Path .\build)) { mkdir build }
+  - cd build
+  - cmake -G "NMake Makefiles JOM" -DCMAKE_Fortran_COMPILER=flang -DCMAKE_BUILD_TYPE=Release -DBUILD_TESTING=ON ..
+
+build_script:
+  - cmake --build .
+
+test_script:
+  - ctest -j2

lapack-netlib/.gitignore

@@ -35,3 +35,9 @@ LAPACKE/example/xexample*
 # SED
 SRC/*-e
 LAPACKE/src/*-e
+build*
+
+# DOCS documentation
+DOCS/man
+DOCS/explore-html
+output_err

lapack-netlib/.travis.yml

@@ -1,33 +1,32 @@
-language: cpp
+language: c
+dist: xenial
+group: travis_latest
+
+git:
+  depth: 3
+  quiet: true
 
 addons:
   apt:
-    sources:
-      - george-edison55-precise-backports # cmake
     packages:
-      - cmake
-      - cmake-data
-      - gfortran
-
-os:
-  - linux
-  - osx
-
-env:
-  - CMAKE_BUILD_TYPE=Release
-  - CMAKE_BUILD_TYPE=Coverage
+    - gfortran
 
-install:
-  - if [[ "$TRAVIS_OS_NAME" == "osx" ]];
-    then
-      for pkg in gcc cmake; do
-        if brew list -1 | grep -q "^${pkg}\$"; then
-          brew outdated $pkg || brew upgrade $pkg;
-        else
-          brew install $pkg;
-        fi
-      done
-    fi
+matrix:
+  include:
+  - os: linux
+    env: CMAKE_BUILD_TYPE=Release
+  - os: linux
+    env: CMAKE_BUILD_TYPE=Coverage
+  - os: osx
+    env: CMAKE_BUILD_TYPE=Release
+    before_install:
+    - brew update > /dev/null
+    - brew install gcc > /dev/null
+  - os: osx
+    env: CMAKE_BUILD_TYPE=Coverage
+    before_install:
+    - brew update > /dev/null
+    - brew install gcc > /dev/null
 
 script:
   - export PR=https://api.github.com/repos/$TRAVIS_REPO_SLUG/pulls/$TRAVIS_PULL_REQUEST

lapack-netlib/BLAS/CMakeLists.txt

@@ -6,4 +6,5 @@ configure_file(${CMAKE_CURRENT_SOURCE_DIR}/blas.pc.in ${CMAKE_CURRENT_BINARY_DIR
 install(FILES
   ${CMAKE_CURRENT_BINARY_DIR}/blas.pc
   DESTINATION ${PKG_CONFIG_DIR}
+  COMPONENT Development
   )

lapack-netlib/BLAS/Makefile

@@ -1,13 +1,18 @@
-include ../make.inc
+TOPSRCDIR = ..
+include $(TOPSRCDIR)/make.inc
 
+.PHONY: all
 all: blas
 
+.PHONY: blas
 blas:
 	$(MAKE) -C SRC
 
+.PHONY: blas_testing
 blas_testing: blas
 	$(MAKE) -C TESTING run
 
+.PHONY: clean cleanobj cleanlib cleanexe cleantest
 clean:
 	$(MAKE) -C SRC clean
 	$(MAKE) -C TESTING clean

lapack-netlib/BLAS/SRC/Makefile

@@ -1,5 +1,3 @@
-include ../../make.inc
-
 #######################################################################
 #  This is the makefile to create a library for the BLAS.
 #  The files are grouped as follows:
@@ -55,6 +53,10 @@ include ../../make.inc
 #
 #######################################################################
 
+TOPSRCDIR = ../..
+include $(TOPSRCDIR)/make.inc
+
+.PHONY: all
 all: $(BLASLIB)
 
 #---------------------------------------------------------
@@ -138,33 +140,32 @@ ALLOBJ = $(SBLAS1) $(SBLAS2) $(SBLAS3) $(DBLAS1) $(DBLAS2) $(DBLAS3) \
 	$(ZBLAS2) $(ZBLAS3) $(ALLBLAS)
 
 $(BLASLIB): $(ALLOBJ)
-	$(ARCH) $(ARCHFLAGS) $@ $^
+	$(AR) $(ARFLAGS) $@ $^
 	$(RANLIB) $@
 
+.PHONY: single double complex complex16
 single: $(SBLAS1) $(ALLBLAS) $(SBLAS2) $(SBLAS3)
-	$(ARCH) $(ARCHFLAGS) $(BLASLIB) $^
+	$(AR) $(ARFLAGS) $(BLASLIB) $^
 	$(RANLIB) $(BLASLIB)
 
 double: $(DBLAS1) $(ALLBLAS) $(DBLAS2) $(DBLAS3)
-	$(ARCH) $(ARCHFLAGS) $(BLASLIB) $^
+	$(AR) $(ARFLAGS) $(BLASLIB) $^
 	$(RANLIB) $(BLASLIB)
 
 complex: $(CBLAS1) $(CB1AUX) $(ALLBLAS) $(CBLAS2) $(CBLAS3)
-	$(ARCH) $(ARCHFLAGS) $(BLASLIB) $^
+	$(AR) $(ARFLAGS) $(BLASLIB) $^
 	$(RANLIB) $(BLASLIB)
 
 complex16: $(ZBLAS1) $(ZB1AUX) $(ALLBLAS) $(ZBLAS2) $(ZBLAS3)
-	$(ARCH) $(ARCHFLAGS) $(BLASLIB) $^
+	$(AR) $(ARFLAGS) $(BLASLIB) $^
 	$(RANLIB) $(BLASLIB)
 
 FRC:
 	@FRC=$(FRC)
 
+.PHONY: clean cleanobj cleanlib
 clean: cleanobj cleanlib
 cleanobj:
 	rm -f *.o
 cleanlib:
 	#rm -f $(BLASLIB)  # May point to a system lib, e.g. -lblas
-
-.f.o:
-	$(FORTRAN) $(OPTS) -c -o $@ $<