Release 0.7.0 (#553)

* up-ed the version number

* release notes in CHANGELOG.md

* user manual pdf

CHANGELOG.md

@@ -1,16 +1,23 @@
 # Change Log
 All notable changes to HiOp are documented in this file.
 
+## Version 0.7.0: Fortran interface and misc fixes and improvements:
+- Fortran interface and examples
+- Bug fixing for sparse device linear solvers
+- Implementation of CUDA CSR matrices
+- Iterative refinement within CUSOLVER linear solver class
+- Improved robustness and performance of mixed dense-sparse solver for AMD/HIP
+
 ## Version 0.6.2:  Initial ginkgo solver integration and misc fixes
 This tag provides an initial integration with ginko, fixes a couple of issues, and add options for (outer) iterative refinement.
 
 ## Version 0.6.1: HIP linear algebra workaround and update for RAJA > v0.14  (March 31, 2022)
 This version/tag provides a workaround for an issue in the HIP BLAS and updates the RAJA code to better operate with the newer versions of RAJA.
 
 ## Version 0.6.0: Release of the PriDec optimization and improved GPU computations (March 31, 2022)
-The salient features of v0.6.0 are 
+The salient features of v0.6.0 are
 
-- the release of the primal decomposition (PriDec) solver for structured two-stage problems 
+- the release of the primal decomposition (PriDec) solver for structured two-stage problems
 - improved support for (NVIDIA) GPUs for solving sparse optimization problems via NVIDIA's cuSOLVER API and newly developed condensed optimization kernels.
 
 Other notable capabilities include

CMakeLists.txt

@@ -11,7 +11,7 @@ if (POLICY CMP0074)
   cmake_policy(SET CMP0074 NEW)
 endif ()
 
-project (hiop VERSION "0.6.2")
+project (hiop VERSION "0.7.0")
 
 string(TIMESTAMP HIOP_RELEASE_DATE "%Y-%m-%d")
 

doc/src/techrep_main.tex

@@ -133,7 +133,7 @@
 \vspace{3cm}
 
   {\huge\bfseries \Hi\ -- User Guide} \\[14pt]
-  {\large\bfseries version 0.6}
+  {\large\bfseries version 0.7}
 
 \vspace{3cm}
 
@@ -155,7 +155,7 @@
 \vspace{4.75cm}
 
  \textcolor{violet}{{\large\bfseries Oct 15, 2017} \\
-{\large\bfseries Updated Sep 01, 2022}}
+{\large\bfseries Updated Sep 30, 2022}}
 
 \vspace{0.75cm}
 
@@ -294,7 +294,12 @@ \subsection{Support of host-device computations using (generic)CPU-(NVIDIA/AMD)G
 
 Starting version 0.6, \Hi offers support for offloading computations to AMD GPU accelerators when solving NLPs in the mixed dense-sparse (MDS) form. Support for HIP should be enabled during the build by using \texttt{cmake} options \texttt{-DHIOP\_USE\_GPU}  and \texttt{-DHIOP\_USE\_HIP}, which will result in using the HIP accelerators for the internal linear solves.
 
-\Hi's \texttt{cmake} build system is quite versatile to find the dependencies required to offload computations to the device GPUs since was developed and tested on a few GPU-enabled HPC platforms at Oak Ridge, Lawrence Livermore, and Pacific Northwest National Laboratories. These dependencies consist of CUDA library version 10.1 or later, rocm library version 4.5.0 or later and a recent Magma linear solver library (as well as a physical NVIDIA/AMD GPU device). \Hi offers an extensive build support for using customized NVIDIA libraries, AMD libraries and/or Magma solver as well as for advanced troubleshooting. The user is referred to \texttt{cmake/FindHiopCudaLibraries.cmake}, \texttt{cmake/FindHiopHipLibraries.cmake} and \texttt{cmake/FindHiOpMagma.cmake} scripts.
+\Hi's \texttt{cmake} build system is quite versatile to find the dependencies required to offload computations to the device GPUs since was developed and tested on a few GPU-enabled HPC platforms at Oak Ridge, Lawrence Livermore, and Pacific Northwest National Laboratories. These dependencies consist of CUDA library version 10.1 or later, rocm library version 4.5.0 or later and a recent Magma linear solver library (as well as a physical NVIDIA/AMD GPU device). \Hi offers an extensive build support for using customized NVIDIA libraries, AMD libraries, and/or Magma solver as well as for advanced troubleshooting. The user is referred to the following CMake scripts for more details:
+\begin{itemize}
+\item \texttt{cmake/FindHiopCudaLibraries.cmake}
+\item \texttt{cmake/FindHiopHipLibraries.cmake}
+\item \texttt{cmake/FindHiOpMagma.cmake} scripts.
+\end{itemize}
 
 \warningcp{Note: } Installing NVIDIA CUDA, AMD HIP, and/or building Magma can be quite challenging. The user is encouraged to rely on preinstalled versions of these, as they are available via \texttt{module} utility on virtually all high-performance computing machines. An example of how to satisfy all the GPU dependencies on Summit supercomputer at Oak Ridge National Lab with a one commands are available at \url{https://github.com/LLNL/hiop/blob/master/README_summit.md}.