[release] update changelog

Author: MarcelKoch

CHANGELOG.md

@@ -11,6 +11,106 @@ git log --first-parent
 
 Please visit our wiki [Changelog](https://github.com/ginkgo-project/ginkgo/wiki/Changelog) for unreleased changes.
 
+## Version 1.11.0
+
+The Ginkgo team is proud to announce the new Ginkgo minor release 1.11.0.
+This release brings new features such as:
+- New interface for sparse matrix-matrix multiplication and addition. The new interface can yield speedups, in the case
+  of repeated computations where the matrix values may change, but the matrix structure (i.e. position of non-zero
+  entries) doesn't. 
+- Performance improvements for the distributed SpMV and pipelined CG solver.
+- Better support for ARM platforms and support for ROCm 7 and CUDA 13.
+
+And more!
+
+If you face an issue, please first check our [known issues page](https://github.com/ginkgo-project/ginkgo/wiki/Known-Issues) and the [open issues list](https://github.com/ginkgo-project/ginkgo/issues) and if you do not
+find a solution, feel free to [open a new issue](https://github.com/ginkgo-project/ginkgo/issues/new/choose) or ask a question using the [github discussions](https://github.com/ginkgo-project/ginkgo/discussions).
+
+Supported systems and requirements:
++ For all platforms, CMake 3.16+
++ C++17 compliant compiler
++ Linux and macOS
+  + GCC: 7.0+
+  + clang: 5.0+
+  + Intel compiler: 2019+
+  + Apple Clang: 15.0 is tested. Earlier versions might also work.
+  + NVHPC: 22.7+
+  + Cray Compiler: 14.0.1+
+  + CUDA module: CMake 3.18+, and CUDA 11.0+ or NVHPC 22.7+, Compute Capability 5.3+
+  + HIP module: CMake 3.21+, and ROCm 4.5+
+  + DPC++ module: Intel oneAPI 2023.1+ with oneMKL and oneDPL. Set the CXX compiler to `dpcpp` or `icpx`.
+  + MPI: standard version 3.1+, ideally GPU Aware, for best performance
++ Windows
+  + MinGW: GCC 7.0+
+  + Microsoft Visual Studio: VS 2019+
+  + CUDA module: CUDA 11.0+, Microsoft Visual Studio
+  + OpenMP module: MinGW.
+
+### Behavior changes
+
++ The dummy Git hook that was installed by default to prevent wrongly formatted commits has been removed [#1873](https://github.com/ginkgo-project/ginkgo/pull/1873)
++ The default choice of a collective communicator implementation is a dense communicator rather than a neighborhood communicator. This can be overridden by using a new `distributed::Matrix::create` overload [#1949](https://github.com/ginkgo-project/ginkgo/pull/1949).
+
+### Summary of previous deprecations
+
++ The `experimental::EnableDistributedLinOp` has been removed, `EnableLinOp` can be used instead [#1751](https://github.com/ginkgo-project/ginkgo/pull/1751).
++ The `Executor::run` overload without a name as first parameter has been deprecated [#1667](https://github.com/ginkgo-project/ginkgo/pull/1667)
++ The `device_reset` parameter of CUDA and HIP executors no longer has an effect, and its `allocation_mode` parameters have been deprecated in favor of the `Allocator` interface.
++ The CMake parameter `GINKGO_BUILD_DPCPP` has been deprecated in favor of `GINKGO_BUILD_SYCL`.
++ The `gko::reorder::Rcm` interface has been deprecated in favor of `gko::experimental::reorder::Rcm` based on `Permutation`.
++ The Permutation class' `permute_mask` functionality.
++ Multiple functions with typos (`set_complex_subpsace()`, range functions such as `conj_operaton` etc).
++ `gko::lend()` is not necessary anymore.
++ The classes `RelativeResidualNorm` and `AbsoluteResidualNorm` are deprecated in favor of `ResidualNorm`.
++ The class `AmgxPgm` is deprecated in favor of `Pgm`.
++ Default constructors for the CSR `load_balance` and `automatical` strategies
++ The PolymorphicObject's move-semantic `copy_from` variant
++ The templated `SolverBase` class.
++ The class `MachineTopology` is deprecated in favor of `machine_topology`.
++ Logger constructors and create functions with the `executor` parameter.
++ The virtual, protected, Dense functions `compute_norm1_impl`, `add_scaled_impl`, etc.
++ Logger events for solvers and criterion without the additional `implicit_tau_sq` parameter.
++ The global `gko::solver::default_krylov_dim`, use instead `gko::solver::gmres_default_krylov_dim`.
++ `array::get_num_elems()` has been renamed to `get_size()`
++ `matrix_data::ensure_row_major_order()` has been renamed to `sort_row_major()`
++ `device_matrix_data::get_num_elems()` has been renamed to `get_num_stored_elements()`
++ The CMake parameter `GINKGO_COMPILER_FLAGS` has been superseded by `CMAKE_CXX_FLAGS`, and `GINKGO_CUDA_COMPILER_FLAGS` has been superseded by `CMAKE_CUDA_FLAGS`
++ The `std::initializer_list` overloads of matrix `create` methods and constructors are deprecated in favor of explicit `array` parameters
+
+### Added features
++ The distributed `Vector` supports creating a non-owning sub-vector [#1894](https://github.com/ginkgo-project/ginkgo/pull/1894).
++ The solver benchmark has a new option to test solvers without repeated initialization [#1881](https://github.com/ginkgo-project/ginkgo/pull/1881), [#1916](https://github.com/ginkgo-project/ginkgo/pull/1916).
++ New sparse matrix-matrix multiplication and addition interfaces, including ones that support value updates without structural changes [#1934](https://github.com/ginkgo-project/ginkgo/pull/1934).
+
+### Improvements
++ The file config is checked for invalid entries [#1792](https://github.com/ginkgo-project/ginkgo/pull/1792).
++ Allows `gko::write` for generic LinOps [#1937](https://github.com/ginkgo-project/ginkgo/pull/1937).
++ Improves the config error messages [#1944](https://github.com/ginkgo-project/ginkgo/pull/1944).
++ Improves the support for `Coo` as non-local matrix type in the distributed matrix [#1883](https://github.com/ginkgo-project/ginkgo/pull/1883).
++ Adds more options to the BLAS and solver benchmarks [#1884](https://github.com/ginkgo-project/ginkgo/pull/1884).
++ Merges dot products in the pipelined CG algorithm [#1908](https://github.com/ginkgo-project/ginkgo/pull/1908).
++ Allows specifying stopping criterion parameters with arguments involving narrowing conversions, so that builds are no longer failing with iteration counts of type `int` [#1941](https://github.com/ginkgo-project/ginkgo/pull/1941).
++ Improves the error messages for unsupported ValueType or IndexType [#1945](https://github.com/ginkgo-project/ginkgo/pull/1945).
++ Improves the overlapping of communication and computation in the distributed SpMV by submitting the local SpMV kernel before waiting for the row gatherer to complete [#1882](https://github.com/ginkgo-project/ginkgo/pull/1882).
++ Supports ARM, ROCm 7, and CUDA 13 with CI validation [#1954](https://github.com/ginkgo-project/ginkgo/pull/1954).
++ Improves the apply logging message in the profiler hook to also include the arguments of the apply [#1921](https://github.com/ginkgo-project/ginkgo/pull/1921).
+
+### Fixes
++ Fixes an error when running with MPICH-based MPI implementations [#1875](https://github.com/ginkgo-project/ginkgo/pull/1875).
++ Fixes the inverse iteration example [#1878](https://github.com/ginkgo-project/ginkgo/pull/1878).
++ Fixes ginkgo CMake `try_compile` variable used by the other project with newer CMake [#1895](https://github.com/ginkgo-project/ginkgo/pull/1895).
++ Fixes a missing `typename` issue from MSVC with CUDA [#1904](https://github.com/ginkgo-project/ginkgo/pull/1904).
++ Fixes a strict alias issue [#1903](https://github.com/ginkgo-project/ginkgo/pull/1903).
++ Fixes compilation with MSVC and Intel MPI [#1906](https://github.com/ginkgo-project/ginkgo/pull/1906)
++ Fixes the handling of unsupported CUDA architectures in several functions concerning `float16` and `bfloat16` [#1853](https://github.com/ginkgo-project/ginkgo/pull/1853).
++ Fixes a bug in the matrix assembly for GPU-aware MPI [#1887](https://github.com/ginkgo-project/ginkgo/pull/1887).
++ Fixes a clang 16 issue regarding `dynamic_cast` to a `final` class [#1924](https://github.com/ginkgo-project/ginkgo/pull/1924).
++ Fixes CUDA 13 building issue [#1926](https://github.com/ginkgo-project/ginkgo/pull/1926).
++ Fixes a bug in ParILUT threshold select for larger matrices on GPUs [#1877](https://github.com/ginkgo-project/ginkgo/pull/1877).
++ Fixes the type names of the Kokkos SYCL executor and memory spaces [#1940](https://github.com/ginkgo-project/ginkgo/pull/1940).
++ Fixes the sanitization of numeric values in matrix statistics benchmark [#1950](https://github.com/ginkgo-project/ginkgo/pull/1950).
+
+
 ## Version 1.10.0
 
 The Ginkgo team is proud to announce the new Ginkgo minor release 1.10.0.