Release history

0.7.0 (current development version)

Under construction.

0.6.8 (18 Dec 2016)

  • ADDED: a von Mises distribution sampler (vonmises()).
  • ADDED: div_const() and div_param() transformations.
  • ADDED: Kernel.prepared_call, Kernel.__call__ and StaticKernel.__call__ now return the resulting Event object in case of the OpenCL backend. ComputationCallable.__call__ returns a list of Event objects from the nested kernel calls.
  • FIXED: properly handling the case of an unfinished __init__() in Thread (when __del__() tries to access non-existent attributes).
  • FIXED: an error when using from_trf() without specifying the guiding array in Py3.
  • FIXED: (reported by @mountaindust) Array.copy now actually copies the array contents in CUDA backend.
  • FIXED: (reported by @Philonoist) load_idx/store_idx handled expressions in parameters incorrectly (errors during macro expansion).
  • FIXED: a minor bug in the information displayed during the interactive Thread creation.
  • FIXED: class names in the test suite that produced errors (due to the changed rules for test discovery in py.test).
  • FIXED: updated ReturnValuesPlugin in the test suite to conform to py.test interface changes.

0.6.7 (11 Mar 2016)

  • ADDED: an example of a transposition-based n-dimensional FFT (demo_fftn_with_transpose.py).
  • FIXED: a problem with Beignet OpenCL driver where the INLINE macro was being redefined.
  • FIXED: a bug in Reduce where reduction over a struct type with a nested array produced a template rendering error.
  • FIXED: now taking the minimum time over several attempts instead of the average in several performance tests (as it is done in the rest of the test suite).
  • FIXED: Transpose now calculates the required elementary transpositions in the constructor instead of doing it during the compilation.

0.6.6 (11 May 2015)

  • FIXED: a bug with the NAN constant not being defined in CUDA on Windows.
  • FIXED: (PR by @ringw) copying and arithmetic operations on Reikna arrays now preserve the array type instead of resetting it to PyOpenCL/PyCUDA array.
  • FIXED: a bug in virtual size finding algorithm that could cause get_local_id(ndim)/get_global_id(ndim) being called with an argument out of the range supported by the OpenCL standard, causing compilation fails on some platforms.
  • FIXED: now omitting some of redundant modulus operations in virtual size functions.
  • ADDED: an example of a spectrogram-calculating computation (demo_specgram.py).

0.6.5 (31 Mar 2015)

  • CHANGED: the correspondence for numpy.uintp is not registered by default anymore — this type is not really useful in CPU-GPU interaction.
  • FIXED: (reported by J. Vacher) dtype/ctype correspondences for 64-bit integer types are registered even if the Python interpreter is 32-bit.
  • ADDED: ComputationCallable objects expose the attribute thread.
  • ADDED: FFTShift computation.
  • ADDED: an example of an element-reshuffling transformation.

0.6.4 (29 Sep 2014)

  • CHANGED: renamed power_dtype parameter to exponent_dtype (a more correct term) in pow().
  • FIXED: (PR by @ringw) exception caused by printing CUDA program object.
  • FIXED: pow() (0, 0) now returns 1 as it should.
  • ADDED: an example of FFT with a custom transformation.
  • ADDED: a type check in the FFT constructor.
  • ADDED: an explicit output_dtype parameter for pow().
  • ADDED: Array objects for each backend expose the attribute thread.

0.6.3 (18 Jun 2014)

  • FIXED: (@schreon) a bug preventing the usage of EntrywiseNorm with custom axes.
  • FIXED: (PR by @SyamGadde) removed syntax constructions incompatible with Python 2.6.
  • FIXED: added Python 3.4 to the list of classifiers.

0.6.2 (20 Feb 2014)

  • ADDED: pow() function module in CLUDA.
  • ADDED: a function any_api() that returns some supported GPGPU API module.
  • ADDED: an example of Reduce with a custom data type.
  • FIXED: a Py3 compatibility issue in Reduce introduced in 0.6.1.
  • FIXED: a bug due to the interaction between the implementation of from_trf() and the logic of processing nested computations.
  • FIXED: a bug in FFT leading to undefined behavior on some OpenCL platforms.

0.6.1 (4 Feb 2014)

  • FIXED: Reduce can now pick a decreased work group size if the attached transformations are too demanding.

0.6.0 (27 Dec 2013)

0.5.2 (17 Dec 2013)

  • ADDED: normal_bm() now supports complex dtypes.
  • FIXED: a nested PureParallel can now take several identical argument objects as arguments.
  • FIXED: a nested computation can now take a single input/output argument (e.g. a temporary array) as separate input and output arguments.
  • FIXED: a critical bug in CBRNG that could lead to the counter array not being updated.
  • FIXED: convenience constructors of CBRNG can now properly handle None as samplers_kwds.

0.5.1 (30 Nov 2013)

  • FIXED: a possible infinite loop in compile_static() local size finding algorithm.

0.5.0 (25 Nov 2013)

  • CHANGED: KernelParameter is not derived from Type anymore (although it still retains the corresponding attributes).
  • CHANGED: Predicate now takes a dtype’d value as empty, not a string.
  • CHANGED: The logic of processing struct dtypes was reworked, and adjust_alignment was removed. Instead, one should use align() (which does not take a Thread parameter) to get a dtype with the offsets and itemsize equal to those a compiler would set. On the other hand, ctype_module() attempts to set the alignments such that the field offsets are the same as in the given numpy dtype (unless ignore_alignments flag is set).
  • ADDED: struct dtypes support in c_constant().
  • ADDED: flatten_dtype() helper function.
  • ADDED: added transposed_a and transposed_b keyword parameters to MatrixMul.
  • ADDED: algorithm cascading to Reduce, leading to 3-4 times increase in performance.
  • ADDED: polar_unit() function module in CLUDA.
  • ADDED: support for arrays with 0-dimensional shape as computation and transformation arguments.
  • FIXED: a bug in Reduce, which lead to incorrect results in cases when the reduction power is exactly equal to the maximum one.
  • FIXED: Transpose now works correctly for struct dtypes.
  • FIXED: bounding_power_of_2 now correctly returns 1 instead of 2 being given 1 as an argument.
  • FIXED: compile_static() local size finding algorithm is much less prone to failure now.

0.4.0 (10 Nov 2013)

  • CHANGED: supports_dtype() method moved from Thread to DeviceParameters.
  • CHANGED: fast_math keyword parameter moved from Thread constructor to compile() and compile_static(). It is also False by default, instead of True. Correspondingly, THREAD_FAST_MATH macro was renamed to COMPILE_FAST_MATH.
  • CHANGED: CBRNG modules are using the dtype-to-ctype support. Correspondingly, the C types for keys and counters can be obtained by calling ctype_module() on key_dtype and counter_dtype attributes. The module wrappers still define their types, but their names are using a different naming convention now.
  • ADDED: module generator for nested dtypes (ctype_module()) and a function to get natural field offsets for a given API/device (adjust_alignment).
  • ADDED: fast_math keyword parameter in compile(). In other words, now fast_math can be set per computation.
  • ADDED: ALIGN macro is available in CLUDA kernels.
  • ADDED: support for struct types as Computation arguments (for them, the ctypes attributes contain the corresponding module obtained with ctype_module()).
  • ADDED: support for non-sequential axes in Reduce.
  • FIXED: bug in the interactive Thread creation (reported by James Bergstra).
  • FIXED: Py3-incompatibility in the interactive Thread creation.
  • FIXED: some code paths in virtual size finding algorithm could result in a type error.
  • FIXED: improved the speed of test collection by reusing Thread objects.

0.3.6 (9 Aug 2013)

  • ADDED: the first argument to the Transformation or PureParallel snippet is now a reikna.core.Indices object instead of a list.
  • ADDED: classmethod PureParallel.from_trf(), which allows one to create a pure parallel computation out of a transformation.
  • FIXED: improved Computation.compile() performance for complicated computations by precreating transformation templates.

0.3.5 (6 Aug 2013)

  • FIXED: bug with virtual size algorithms returning floating point global and local sizes in Py2.

0.3.4 (3 Aug 2013)

  • CHANGED: virtual sizes algorithms were rewritten and are now more maintainable. In addition, virtual sizes can now handle any number of dimensions of local and global size, providing the device can support the corresponding total number of work items and groups.
  • CHANGED: id- and size- getting kernel functions now have return types corresponding to their equivalents. Virtual size functions have their own independent return type.
  • CHANGED: Thread.compile_static() and ComputationPlan.kernel_call() take global and local sizes in the row-major order, to correspond to the matrix indexing in load/store macros.
  • FIXED: requirements for PyCUDA extras (a currently non-existent version was specified).
  • FIXED: an error in gamma distribution sampler, which lead to slightly wrong shape of the resulting distribution.

0.3.3 (29 Jul 2013)

  • FIXED: package metadata.

0.3.2 (29 Jul 2013)

  • ADDED: same module object, when being called without arguments from other modules/snippets, is rendered only once and returns the same prefix each time. This allows one to create structure declarations that can be used by functions in several modules.
  • ADDED: reworked cbrng module and exposed kernel interface of bijections and samplers.
  • CHANGED: slightly changed the algorithm that determines the order of computation parameters after a transformation is connected to it. Now the ordering inside a list of initial computation parameters or a list of a single transformation parameters is preserved.
  • CHANGED: kernel declaration string is now passed explicitly to a kernel template as the first parameter.
  • FIXED: typo in FFT performance test.
  • FIXED: bug in FFT that could result in changing the contents of the input array to one of the intermediate results.
  • FIXED: missing data type normalization in c_constant().
  • FIXED: Py3 incompatibility in cluda.cuda.
  • FIXED: updated some obsolete computation docstrings.

0.3.1 (25 Jul 2013)

  • FIXED: too strict array type check for nested computations that caused some tests to fail.
  • FIXED: default values of scalar parameters are now processed correctly.
  • FIXED: Mako threw name-not-found exceptions on some list comprehensions in FFT template.
  • FIXED: some earlier-introduced errors in tests.
  • INTERNAL: pylint was ran and many stylistic errors fixed.

0.3.0 (23 Jul 2013)

Major core API change:

  • Computations have function-like signatures with the standard Signature interface; no more separation of inputs/outputs/scalars.
  • Generic transformations were ditched; all the transformations have static types now.
  • Transformations can now change array shapes, and load/store from/to external arrays in output/input transformations.
  • No flat array access in kernels; all access goes through indices. This opens the road for correct and automatic stride support (not fully implemented yet).
  • Computations and accompanying classes are stateless, and their creation is more straightforward.

Other stuff:

  • Bumped Python requirements to >=2.6 or >=3.2, and added a dependency on funcsig.
  • ADDED: more tests for cluda.functions.
  • ADDED: module/snippet attributes discovery protocol for custom objects.
  • ADDED: strides support to array allocation functions in CLUDA.
  • ADDED: modules can now take positional arguments on instantiation, same as snippets.
  • CHANGED: Elementwise becomes PureParallel (as it is not always elementwise).
  • FIXED: incorrect behavior of functions.norm() for non-complex arguments.
  • FIXED: undefined variable in functions.exp() template (reported by Thibault North).
  • FIXED: inconsistent block/grid shapes in static kernels

0.2.4 (11 May 2013)

  • ADDED: ability to introduce new scalar arguments for nested computations (the API is quite ugly at the moment).
  • FIXED: handling prefixes properly when connecting transformations to nested computations.
  • FIXED: bug in dependency inference algorithm which caused it to ignore allocations in nested computations.

0.2.3 (25 Apr 2013)

  • ADDED: explicit release() (primarily for certain rare CUDA use cases).
  • CHANGED: CLUDA API discovery interface (see the documentation).
  • CHANGED: The part of CLUDA API that is supposed to be used by other layers was moved to the __init__.py.
  • CHANGED: CLUDA Context was renamed to Thread, to avoid confusion with PyCUDA/PyOpenCL contexts.
  • CHANGED: signature of create(); it can filter devices now, and supports interactive mode.
  • CHANGED: Module with snippet=True is now Snippet
  • FIXED: added transformation.mako and cbrng_ref.py to the distribution package.
  • FIXED: incorrect parameter generation in test/cluda/cluda_vsizes/ids.
  • FIXED: skipping testcases with incompatible parameters in test/cluda/cluda_vsizes/ids and sizes.
  • FIXED: setting the correct length of max_num_groups in case of CUDA and a device with CC < 2.
  • FIXED: typo in cluda.api_discovery.

0.2.2 (20 Apr 2013)

  • ADDED: ability to use custom argument names in transformations.
  • ADDED: multi-argument mul().
  • ADDED: counter-based random number generator CBRNG.
  • ADDED: reikna.elementwise.Elementwise now supports argument dependencies.
  • ADDED: Module support in CLUDA; see Tutorial: modules and snippets for details.
  • ADDED: template_def().
  • CHANGED: reikna.cluda.kernel.render_template_source is the main renderer now.
  • CHANGED: FuncCollector class was removed; functions are now used as common modules.
  • CHANGED: all templates created with template_for() are now rendered with from __future__ import division.
  • CHANGED: signature of OperationRecorder.add_kernel takes a renderable instead of a full template.
  • CHANGED: compile_static() now takes a template instead of a source.
  • CHANGED: reikna.elementwise.Elementwise now uses modules.
  • FIXED: potential problem with local size finidng in static kernels (first approximation for the maximum workgroup size was not that good)
  • FIXED: some OpenCL compilation warnings caused by an incorrect version querying macro.
  • FIXED: bug with incorrect processing of scalar global size in static kernels.
  • FIXED: bug in variance estimates in CBRNG tests.
  • FIXED: error in the temporary varaiable type in reikna.cluda.functions.polar() and reikna.cluda.functions.exp().

0.2.1 (8 Mar 2013)

  • FIXED: function names for kernel polar(), exp() and conj().
  • FIXED: added forgotten kernel norm() handler.
  • FIXED: bug in Py.Test testcase execution hook which caused every test to run twice.
  • FIXED: bug in nested computation processing for computation with more than one kernel.
  • FIXED: added dependencies between MatrixMul kernel arguments.
  • FIXED: taking into account dependencies between input and output arrays as well as the ones between internal allocations — necessary for nested computations.
  • ADDED: discrete harmonic transform DHT (calculated using Gauss-Hermite quadrature).

0.2.0 (3 Mar 2013)

  • Added FFT computation (slightly optimized PyFFT version + Bluestein’s algorithm for non-power-of-2 FFT sizes)
  • Added Python 3 compatibility
  • Added Thread-global automatic memory packing
  • Added polar(), conj() and exp() functions to kernel toolbox
  • Changed name because of the clash with another Tigger.

0.1.0 (12 Sep 2012)

  • Lots of changes in the API
  • Added elementwise, reduction and transposition computations
  • Extended API reference and added topical guides

0.0.1 (22 Jul 2012)

  • Created basic core for computations and transformations
  • Added matrix multiplication computation
  • Created basic documentation