Merge branch 'release0.20' into gold/2021

Author: Diptorup Deb

.flake8

@@ -18,3 +18,4 @@ exclude =
     __pycache__,
     _version.py,
     lowerer.py,
+    parfor.py

CHANGELOG.md

@@ -4,6 +4,72 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [0.20.0] - 2023-03-06
+
+### Added
+* New dpjit decorator supporting dpnp compilation (#887)
+* Boxing and unboxing functionality for dpnp.ndarray to numba_dpex (#902)
+* New DpexTarget and dispatcher for compiling dpnp using numba-dpex (#887)
+* Overload implementation for dpnp.empty (#902)
+* Overload implementation for dpnp.empty_like, dpnp.zeros_like and
+  dpnp.ones_like inside dpjit (#928)
+* Overload implementation for dpnp.zeros and dpnp.ones inside dpjit (#923)
+* Compilation and offload support for dpnp vector style expressions using Numba
+  parfors (#957)
+* Compilation of over 70 ufuncs for dpnp inside dpjit (#957)
+* Backported the split parfor pass from upstream Numba. (#949)
+* Numba type aliases to numba_dpex. (#851)
+* Numba prange alias inside numba_dpex. (#957)
+* New LRU cache for kernels (#804) and funcs (#877)
+* New Range and NdRange classes for kernel submission that follow sycl's range
+  and ndrange syntax. (#888)
+* Monkey pacthes to Numba 0.56.4 to support dpnp ufuncs, allocating dpnp
+  arrays (#954)
+* New config flag (NUMBA_DPEX_DUMP_KERNEL_LLVM) to dump a kernel's
+  LLVM IR (#924)
+* A badge to our gitter chatroom (#919)
+* A small script to update copyright headers (#917)
+* A new dpexrt_python extension to support USM allocators for Numba
+  NRT_MemInfo (#902)
+* Updated examples for kernel API demonstrating compute-follows-data programming
+  model. (#826)
+
+### Changed
+* `CLK_GLOBAL_MEM_FENCE` and `CLK_LOCAL_MEM_FENCE` flags renamed to
+  `GLOBAL_MEM_FENCE` and `LOCAL_MEM_FENCE`. (#844)
+* Switched from Ubuntu-latest to Ubuntu-20.04 for conda package build (#836)
+* Rename USMNdArrayType to USMNdArray (#851)
+* Changes to the Numba type to represent dpnp ndarray typess now renamed to
+  DpnpNdarray (#880)
+* Improved exceptions and user errors (#804)
+* Updated internal API for kernel interface with improved support for
+  `__sycl_usm_array_interface__` protocol (#804)
+* Pin generated spirv version for kernels to 1.1 (#885)
+* Rename DpexContext and DpexTypingContext to DpexKernelTarget and
+  DpexKernelTypingContext (#887)
+* Renamed existing dpnp overloads that used stubs to dpnp_stubs_impl.py (#953)
+* Dpctl version requirement mismatch is now a warning and not an
+  ImportError (#925)
+* Update to versioneer 0.28 (#827)
+* Update to dpctl 0.14 (#858)
+* Update linters: black to 23.1.0, isort to 5.12.0 (#900)
+* License in setup.py to match actual project licensing (#904)
+### Fixed
+* Kernel specialization, compute follows data programming model for
+  kernels (#804)
+* Dispatcher/caching rewrite to address performance regression (#912, #896)
+* func decorator qualname ambiguation fix (#905)
+
+### Removed
+* Removes the numpy_usm_shared module from numba_dpex. (#841)
+* Removes the usage of llvmlite.llvmpy (#932)
+
+### Deprecated
+* Support for NumPy arrays as kernel arguments (#804)
+* Kernel argument access specifiers (#804)
+* Support for dpctl.device_context to launch kernels and njit offloading (#804)
+* Dpnp overloads using stubs. (#953)
+
 ## [0.19.0] - 2022-11-21
 
 ### Added

README.md

@@ -1,7 +1,7 @@
 [![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)
 [![Coverage Status](https://coveralls.io/repos/github/IntelPython/numba-dpex/badge.svg?branch=main)](https://coveralls.io/github/IntelPython/numba-dpex?branch=main)
 [![pre-commit](https://img.shields.io/badge/pre--commit-enabled-brightgreen?logo=pre-commit&logoColor=white)](https://github.com/pre-commit/pre-commit)
-
+[![Join the chat at https://matrix.to/#/#Data-Parallel-Python_community:gitter.im](https://badges.gitter.im/Join%20Chat.svg)](https://app.gitter.im/#/room/#Data-Parallel-Python_community:gitter.im)
 <img align="left" src="https://spec.oneapi.io/oneapi-logo-white-scaled.jpg" alt="oneAPI logo" width="75"/>
 <br/>
 <br/>

docs/conf.py

@@ -21,7 +21,7 @@
 # -- Project information -----------------------------------------------------
 
 project = "numba-dpex"
-copyright = "2021,2022 Intel"
+copyright = "2021-2023 Intel Corporation"
 author = "Intel"
 
 # The full version, including alpha/beta/rc tags
@@ -40,8 +40,12 @@
     "sphinx.ext.todo",
     "sphinx.ext.intersphinx",
     "sphinxcontrib.apidoc",
+    "sphinxcontrib.googleanalytics",
 ]
 
+googleanalytics_id = "G-LGGL0NJK6P"
+googleanalytics_enabled = True
+
 todo_include_todos = True
 
 source_parsers = {".md": "recommonmark.parser.CommonMarkParser"}

environment/docs.yml

@@ -31,6 +31,7 @@ dependencies:
     - recommonmark
     - sphinx-rtd-theme
     - sphinxcontrib-apidoc
+    - sphinxcontrib-googleanalytics
 variables:
   CHANNELS: -c defaults -c numba -c intel -c numba/label/dev -c dppy/label/dev --override-channels
   CHANNELS_DEV: -c dppy/label/dev -c defaults -c numba -c intel -c numba/label/dev --override-channels

numba_dpex/__init__.py

@@ -5,33 +5,132 @@
 """
 The numba-dpex extension module adds data-parallel offload support to Numba.
 """
+import glob
+import logging
+import os
+import platform as plt
 
-import numba_dpex.core.dpjit_dispatcher
-import numba_dpex.core.offload_dispatcher
+import dpctl
+import llvmlite.binding as ll
+import numba
+from numba.core import ir_utils
+from numba.np import arrayobj
+from numba.np.ufunc import array_exprs
+from numba.np.ufunc.decorators import Vectorize
+
+from numba_dpex._patches import _empty_nd_impl, _is_ufunc, _mk_alloc
+from numba_dpex.vectorizers import Vectorize as DpexVectorize
+
+# Monkey patches
+array_exprs._is_ufunc = _is_ufunc
+ir_utils.mk_alloc = _mk_alloc
+arrayobj._empty_nd_impl = _empty_nd_impl
+
+
+def load_dpctl_sycl_interface():
+    """Permanently loads the ``DPCTLSyclInterface`` library provided by dpctl.
+    The ``DPCTLSyclInterface`` library provides C wrappers over SYCL functions
+    that are directly invoked from the LLVM modules generated by numba_dpex.
+    We load the library once at the time of initialization using llvmlite's
+    load_library_permanently function.
+    Raises:
+        ImportError: If the ``DPCTLSyclInterface`` library could not be loaded.
+    """
+
+    platform = plt.system()
+    if platform == "Windows":
+        paths = glob.glob(
+            os.path.join(
+                os.path.dirname(dpctl.__file__), "*DPCTLSyclInterface.dll"
+            )
+        )
+    else:
+        paths = glob.glob(
+            os.path.join(
+                os.path.dirname(dpctl.__file__), "*DPCTLSyclInterface.so.0"
+            )
+        )
+
+    if len(paths) == 1:
+        ll.load_library_permanently(paths[0])
+    else:
+        raise ImportError
+
+    Vectorize.target_registry.ondemand["dpex"] = lambda: DpexVectorize
+
+
+numba_version = tuple(map(int, numba.__version__.split(".")[:3]))
+if numba_version < (0, 56, 4):
+    logging.warning(
+        "numba_dpex needs numba 0.56.4, using "
+        f"numba={numba_version} may cause unexpected behavior"
+    )
+
+
+dpctl_version = tuple(map(int, dpctl.__version__.split(".")[:2]))
+if dpctl_version < (0, 14):
+    logging.warning(
+        "numba_dpex needs dpctl 0.14 or greater, using "
+        f"dpctl={dpctl_version} may cause unexpected behavior"
+    )
+
+from numba import prange  # noqa E402
+
+import numba_dpex.core.dpjit_dispatcher  # noqa E402
+import numba_dpex.core.offload_dispatcher  # noqa E402
 
 # Initialize the _dpexrt_python extension
-import numba_dpex.core.runtime
-import numba_dpex.core.targets.dpjit_target
+import numba_dpex.core.runtime  # noqa E402
+import numba_dpex.core.targets.dpjit_target  # noqa E402
 
 # Re-export types itself
-import numba_dpex.core.types as types
-from numba_dpex.core.kernel_interface.utils import *
+import numba_dpex.core.types as types  # noqa E402
+from numba_dpex import config  # noqa E402
+from numba_dpex.core.kernel_interface.indexers import (  # noqa E402
+    NdRange,
+    Range,
+)
 
 # Re-export all type names
-from numba_dpex.core.types import *
-from numba_dpex.retarget import offload_to_sycl_device
-
-from . import config
+from numba_dpex.core.types import *  # noqa E402
+from numba_dpex.dpnp_iface import dpnpimpl  # noqa E402
+from numba_dpex.retarget import offload_to_sycl_device  # noqa E402
 
 if config.HAS_NON_HOST_DEVICE:
-    from .device_init import *
+    # Re export
+    from .core.targets import dpjit_target, kernel_target
+    from .decorators import dpjit, func, kernel
+
+    # We are importing dpnp stub module to make Numba recognize the
+    # module when we rename Numpy functions.
+    from .dpnp_iface.stubs import dpnp
+    from .ocl.stubs import (
+        GLOBAL_MEM_FENCE,
+        LOCAL_MEM_FENCE,
+        atomic,
+        barrier,
+        get_global_id,
+        get_global_size,
+        get_group_id,
+        get_local_id,
+        get_local_size,
+        get_num_groups,
+        get_work_dim,
+        local,
+        mem_fence,
+        private,
+        sub_group_barrier,
+    )
+
+    DEFAULT_LOCAL_SIZE = []
+    load_dpctl_sycl_interface()
+    del load_dpctl_sycl_interface
 else:
     raise ImportError("No non-host SYCL device found to execute kernels.")
 
-
-from ._version import get_versions
+from numba_dpex._version import get_versions  # noqa E402
 
 __version__ = get_versions()["version"]
 del get_versions
 
-__all__ = ["offload_to_sycl_device"] + types.__all__
+__all__ = types.__all__ + ["offload_to_sycl_device"] + ["Range", "NdRange"]