CLBlast version 1.6.3. Changes since previous release (version 1.6.2):

• Fixed a bug in the GEMMK=1 kernel (with 2D register tiling) when MWG!=NWG
• CMake fixes for older versions and for the CUDA backend
• Added tuned parameters for many devices (see doc/tuning.md)

CLBlast version 1.6.2. Changes since previous release (version 1.6.1):

• Fix a bug in the pre-processor that would cause issues on Arm GPUs
• Fix DLL install directory in mingw
• Modifications to the Python bindings (pyclblast)
  • Convert float scalar values to cl_half for fp16 routines
  • Amax/amin, max/min routines accept unsigned integer buffers for index
  • Switch to pyproject.toml file for installing Python bindings
  • Build Python bindings using Cmake, adding Windows support
• Generator script now always use LF endings, independent of the platform
• Added tuned parameters for many devices (see doc/tuning.md)

CLBlast version 1.6.1. Changes since previous release (version 1.6.0):

• Fix pointer error in pyclblast on ARM
• Fix a multithreading bug related to storing objects in the cache
• Added tuned parameters for many devices (see doc/tuning.md)

CLBlast version 1.6.0. Changes since previous release (version 1.5.3):

• Improved performance on Qualcomm Adreno GPUs:
  • Unique database entries for specific Adreno devices
  • Toggle OpenCL kernel compilation options for Adreno
  • New preprocessor directive RELAX_WORKGROUP_SIZE
• Fixed a bug in handling of #undef in CLBlast loop unrolling and array-to-register mapping functions
• Fixed a bug in XAMAX/XAMIN routines related to inadvertently including the increment and offset in the result
• Fixed a bug in XAMAX/XAMIN routines that would cause only the real part of a complex number to be taken into account
• Fixed a bug that caused tests to not properly do integer-output testing (for XAMAX/XAMIN)
• Fixes a minor issue with the expected input buffer size in the TRMV/TBMV/TPMV/TRSV routines
• Fixes an issue with crashes on Android related to calling clReleaseProgram
• Fixes two small issues in the plotting script
• Fixed a documentation bug in the 'ld' requirements
• Enabled Github Actions CI builds for testing and releasing
• Various minor fixes and enhancements
• Added tuned parameters for various devices (see doc/tuning.md)

CLBlast version 1.5.3. Changes since previous release (version 1.5.2):

• Fix a correctness issue with DGEMM on SM 7.5 Turing GPUs
• Update cl.hpp to the new opencl.hpp header in the samples
• Changed the complex sum routine to return the complex sum instead of the absolute complex sum.
• Various minor fixes and enhancements
• Added tuned parameters for various devices (see doc/tuning.md)

CLBlast version 1.5.2. Changes since previous release (version 1.5.1):

• Changed XAMAX/XAMIN to more likely return first rather than last min/max index, updated API docs
• Added batched routines to pyclblast
• Added CLBLAST_VERSION_MAJOR/MINOR/PATCH defines in headers to store version numbering
• Several small improvements to the benchmark script (thanks to 'baryluk')
• Fixed a bug in the caching when using a context with multiple devices
• Fixed a bug in the tuners related to global workgroup size not being a multiple of the local
• Various minor fixes and enhancements
• Added tuned parameters for various devices (see doc/tuning.md)

CLBlast version 1.5.1. Changes since previous release (version 1.5.0):

• Implemented single-kernel version of convolution as GEMM
• Now catches all exceptions thrown by the tuners
• Fixed a bug in ISAMIN kernel
• Fixed an out-of-bounds read/write in the XHAD routine (thanks to etomzak)
• Various minor fixes and enhancements
• Added tuned parameters for various devices (see doc/tuning.md)

CLBlast version 1.5.0. Changes since previous release (version 1.4.1):

• Added support for shuffle instructions for NVIDIA GPUs (thanks to 'tyler-utah')
• Added an option to compile the Netlib API with static OpenCL device and context (-DNETLIB_PERSISTENT_OPENCL=ON)
• Added a FAQ page to the documentation
• The tuners now check beforehand on invalid local thread sizes and skip those completely
• Made the tuning API (OverrideParameters) more flexible, disregarding superfluous parameters
• Fixed an issue with conjugate transpose not being executed in certain cases for a.o. XOMATCOPY
• Fixed an issue with AMD GPUs and the new GEMMK == 1 kernel
• Fixed an issue with the preprocessor and the new GEMMK == 1 kernel
• Fixed an issue for unequal MWG and NWG and the new GEMMK == 1 kernel
• Fixed an issue for certain parameters for AXPY's 'XaxpyFaster' kernel
• Various minor fixes and enhancements
• Added non-BLAS routines:
  • SCONVGEMM/DCONVGEMM/HCONVGEMM (convolution as im2col followed by batched GEMM)
  • SCOL2IM/DCOL2IM/CCOL2IM/ZCOL2IM/HCOL2IM (col2im transform as used in machine learning)

CLBlast version 1.4.1 (bugfix release). Changes since previous release (version 1.4.0):

• Fixed an access violation under Windows upon releasing the OpenCL program when the driver is already unloaded
• Fixed an issue with double cl_program release in the CLBlast caching system
• Added tuned parameters for various devices (see doc/tuning.md)

CLBlast version 1.4.0. Changes since previous release (version 1.3.0):

• Added Python interface to CLBlast 'PyCLBlast'
• Added CLBlast to Ubuntu PPA and macOS Homebrew package managers
• Added an API to run the tuners programmatically without any I/O
• Improved the performance potential by adding a second tunable GEMM kernel with 2D register tiling
• Added support for Intel specific subgroup shuffling extensions for faster GEMM on Intel GPUs
• Re-added a local memory size constraint to the tuners
• The routine tuners now automatically pick up tuning results from disk from the kernel tuners
• Updated and reorganised the CLBlast documentation
• Added a 'canary' region to check for overflows in the tuner and tests (inspired by clARMOR)
• Added an option to test against and compare performance with Intel's MKL
• Fixed an access violation when compiled with Visual Studio upon releasing the OpenCL program
• Fixed incorrect releasing of the OpenCL program resulting in segfaults / access violations
• Various minor fixes and enhancements
• Added tuned parameters for various devices (see doc/tuning.md)
• Added non-BLAS level-1 routines:
  • SHAD/DHAD/CHAD/ZHAD/HHAD (Hadamard element-wise vector-vector product)