diff --git a/dev/.buildinfo b/dev/.buildinfo index 77a4166588..8212edc04d 100644 --- a/dev/.buildinfo +++ b/dev/.buildinfo @@ -1,4 +1,4 @@ # Sphinx build info version 1 # This file hashes the configuration used when building these files. When it is not found, a full rebuild will be done. -config: 792aaac086a9c34e1e99219e7eb06ccb +config: d78f5c1e9ab2aab5ca5c3fe176d311b5 tags: 645f666f9bcd5a90fca523b33c5a78b7 diff --git a/dev/_sources/autoapi/numba_dpex/kernel_api/barrier/index.rst.txt b/dev/_sources/autoapi/numba_dpex/kernel_api/barrier/index.rst.txt index 0b97d3fa72..726b64845b 100644 --- a/dev/_sources/autoapi/numba_dpex/kernel_api/barrier/index.rst.txt +++ b/dev/_sources/autoapi/numba_dpex/kernel_api/barrier/index.rst.txt @@ -34,11 +34,7 @@ Functions The function is modeled after the ``sycl::group_barrier`` function. It synchronizes work within a group of work items. All the work-items of the group must execute the barrier construct before any work-item - continues execution beyond the barrier. However, unlike - ``sycl::group_barrier`` the numba_dpex function implicitly synchronizes at - the level of a work group and does not allow specifying the group as an - argument. The :func:`sub_group_barrier` function should be used if - synchronization has to be performed only across a sub-group. + continues execution beyond the barrier. The ``group_barrier`` performs mem-fence operations ensuring that memory accesses issued before the barrier are not re-ordered with those issued diff --git a/dev/_sources/autoapi/numba_dpex/kernel_api/index.rst.txt b/dev/_sources/autoapi/numba_dpex/kernel_api/index.rst.txt index 539bb7d2f5..c068b9b52a 100644 --- a/dev/_sources/autoapi/numba_dpex/kernel_api/index.rst.txt +++ b/dev/_sources/autoapi/numba_dpex/kernel_api/index.rst.txt @@ -799,11 +799,7 @@ Functions The function is modeled after the ``sycl::group_barrier`` function. It synchronizes work within a group of work items. All the work-items of the group must execute the barrier construct before any work-item - continues execution beyond the barrier. However, unlike - ``sycl::group_barrier`` the numba_dpex function implicitly synchronizes at - the level of a work group and does not allow specifying the group as an - argument. The :func:`sub_group_barrier` function should be used if - synchronization has to be performed only across a sub-group. + continues execution beyond the barrier. The ``group_barrier`` performs mem-fence operations ensuring that memory accesses issued before the barrier are not re-ordered with those issued diff --git a/dev/autoapi/numba_dpex/kernel_api/barrier/index.html b/dev/autoapi/numba_dpex/kernel_api/barrier/index.html index 592a216c68..faf54f2ec5 100644 --- a/dev/autoapi/numba_dpex/kernel_api/barrier/index.html +++ b/dev/autoapi/numba_dpex/kernel_api/barrier/index.html @@ -288,11 +288,7 @@

Functionssycl::group_barrier function. It synchronizes work within a group of work items. All the work-items of the group must execute the barrier construct before any work-item -continues execution beyond the barrier. However, unlike -sycl::group_barrier the numba_dpex function implicitly synchronizes at -the level of a work group and does not allow specifying the group as an -argument. The sub_group_barrier() function should be used if -synchronization has to be performed only across a sub-group.

+continues execution beyond the barrier.

The group_barrier performs mem-fence operations ensuring that memory accesses issued before the barrier are not re-ordered with those issued after the barrier: all work-items in group g execute a release fence prior diff --git a/dev/autoapi/numba_dpex/kernel_api/index.html b/dev/autoapi/numba_dpex/kernel_api/index.html index 2dae1d17fc..6e2a3b9ed9 100644 --- a/dev/autoapi/numba_dpex/kernel_api/index.html +++ b/dev/autoapi/numba_dpex/kernel_api/index.html @@ -1245,11 +1245,7 @@

Functionssycl::group_barrier function. It synchronizes work within a group of work items. All the work-items of the group must execute the barrier construct before any work-item -continues execution beyond the barrier. However, unlike -sycl::group_barrier the numba_dpex function implicitly synchronizes at -the level of a work group and does not allow specifying the group as an -argument. The sub_group_barrier() function should be used if -synchronization has to be performed only across a sub-group.

+continues execution beyond the barrier.

The group_barrier performs mem-fence operations ensuring that memory accesses issued before the barrier are not re-ordered with those issued after the barrier: all work-items in group g execute a release fence prior diff --git a/dev/searchindex.js b/dev/searchindex.js index 634c6c4288..739194e37b 100644 --- a/dev/searchindex.js +++ b/dev/searchindex.js @@ -1 +1 @@ -Search.setIndex({"docnames": ["autoapi/index", "autoapi/numba_dpex/kernel_api/atomic_ref/index", "autoapi/numba_dpex/kernel_api/barrier/index", "autoapi/numba_dpex/kernel_api/flag_enum/index", "autoapi/numba_dpex/kernel_api/index", "autoapi/numba_dpex/kernel_api/index_space_ids/index", "autoapi/numba_dpex/kernel_api/launcher/index", "autoapi/numba_dpex/kernel_api/memory_enums/index", "autoapi/numba_dpex/kernel_api/ranges/index", "contribution_guide", "examples", "getting_started", "glossary", "index", "license", "overview", "programming_model", "release-notes", "useful_links", "user_guide/config", "user_guide/debugging/altering", "user_guide/debugging/backtrace", "user_guide/debugging/breakpoints", "user_guide/debugging/common_issues", "user_guide/debugging/data", "user_guide/debugging/debugging_environment", "user_guide/debugging/features", "user_guide/debugging/frame_info", "user_guide/debugging/index", "user_guide/debugging/limitations", "user_guide/debugging/local_variables", "user_guide/debugging/numba-0.55", "user_guide/debugging/set_up_machine", "user_guide/debugging/stepping", "user_guide/debugging/symbols", "user_guide/dpnp_offload", "user_guide/index", "user_guide/kernel_programming/atomic-operations", "user_guide/kernel_programming/device-functions", "user_guide/kernel_programming/index", "user_guide/kernel_programming/memory_allocation_address_space", "user_guide/kernel_programming/random", "user_guide/kernel_programming/reduction", "user_guide/kernel_programming/supported-python-features", "user_guide/kernel_programming/synchronization", "user_guide/kernel_programming/ufunc", "user_guide/kernel_programming/writing_kernels"], "filenames": ["autoapi/index.rst", "autoapi/numba_dpex/kernel_api/atomic_ref/index.rst", "autoapi/numba_dpex/kernel_api/barrier/index.rst", "autoapi/numba_dpex/kernel_api/flag_enum/index.rst", "autoapi/numba_dpex/kernel_api/index.rst", "autoapi/numba_dpex/kernel_api/index_space_ids/index.rst", "autoapi/numba_dpex/kernel_api/launcher/index.rst", "autoapi/numba_dpex/kernel_api/memory_enums/index.rst", "autoapi/numba_dpex/kernel_api/ranges/index.rst", "contribution_guide.rst", "examples.rst", "getting_started.rst", "glossary.rst", "index.rst", "license.rst", "overview.rst", "programming_model.rst", "release-notes.rst", "useful_links.rst", "user_guide/config.rst", "user_guide/debugging/altering.rst", "user_guide/debugging/backtrace.rst", "user_guide/debugging/breakpoints.rst", "user_guide/debugging/common_issues.rst", "user_guide/debugging/data.rst", "user_guide/debugging/debugging_environment.rst", "user_guide/debugging/features.rst", "user_guide/debugging/frame_info.rst", "user_guide/debugging/index.rst", "user_guide/debugging/limitations.rst", "user_guide/debugging/local_variables.rst", "user_guide/debugging/numba-0.55.rst", "user_guide/debugging/set_up_machine.rst", "user_guide/debugging/stepping.rst", "user_guide/debugging/symbols.rst", "user_guide/dpnp_offload.rst", "user_guide/index.rst", "user_guide/kernel_programming/atomic-operations.rst", "user_guide/kernel_programming/device-functions.rst", "user_guide/kernel_programming/index.rst", "user_guide/kernel_programming/memory_allocation_address_space.rst", "user_guide/kernel_programming/random.rst", "user_guide/kernel_programming/reduction.rst", "user_guide/kernel_programming/supported-python-features.rst", "user_guide/kernel_programming/synchronization.rst", "user_guide/kernel_programming/ufunc.rst", "user_guide/kernel_programming/writing_kernels.rst"], "titles": ["API Reference", "numba_dpex.kernel_api.atomic_ref", "numba_dpex.kernel_api.barrier", "numba_dpex.kernel_api.flag_enum", "numba_dpex.kernel_api", "numba_dpex.kernel_api.index_space_ids", "numba_dpex.kernel_api.launcher", "numba_dpex.kernel_api.memory_enums", "numba_dpex.kernel_api.ranges", "Contribution Guide", "List of examples", "Getting Started", "Glossary", "Data Parallel Extension for Numba*", "License", "Overview", "Programming Model", "Release Notes", "Useful links", "Configuration Options for numba-dpex", "Altering Execution", "Backtrace", "Breakpoints", "Common issues and tips", "Examining Data", "Configure debugging environment", "Supported Features", "Information About a Frame", "Debugging with Intel\u00ae Distribution for GDB*", "Limitations", "Debugging Local Variables", "Debugging Features in Numba 0.55", "Set up the machine for debugging", "Stepping", "Examining the Symbol Table", "Compiling and Offloading dpnp statements", "Tutorials", "Supported Atomic Operations", "Writing Device Functions", "Kernel Programming Basics", "Supported Address Space Qualifiers", "Random Number Generation", "Reduction on SYCL-supported Devices", "Supported Python Features inside numba_dpex.kernel", "Synchronization Functions", "Universal Functions", "Writing Data Parallel Kernels"], "terms": {"thi": [0, 4, 5, 8, 14, 16, 17, 20, 23, 24, 28, 30, 32, 33, 40, 42, 43, 44, 46], "page": [0, 11, 15, 17, 28, 32, 43], "contain": [0, 1, 4, 8, 11], "auto": [0, 16, 23], "gener": [0, 4, 7, 16, 17, 19, 21, 43], "document": [0, 13, 17, 20, 23, 24, 27, 28, 29, 30, 34], "1": [0, 4, 7, 8, 16, 19, 20, 21, 22, 23, 24, 25, 27, 28, 31, 33, 34, 35, 37, 38, 39, 40, 41, 46], "numba_dpex": [0, 11, 13, 15, 16, 17, 19, 20, 21, 22, 23, 24, 25, 27, 28, 30, 31, 33, 34, 35, 36, 37, 38, 39, 40, 42, 44, 46], "kernel_api": [0, 13], "submodul": [0, 17], "overview": [0, 13], "class": [0, 17, 37, 46], "function": [0, 1, 5, 15, 16, 17, 18, 20, 21, 23, 26, 29, 30, 33, 35, 36, 37, 39, 40, 42], "creat": [0, 11, 16, 17, 25, 28, 32, 40, 45], "sphinx": 0, "autoapi": 0, "implement": [1, 4, 5, 6, 7, 15, 16, 17, 18, 32, 37, 38, 40, 42, 44, 46], "mock": [1, 4, 5, 6], "python": [1, 2, 4, 5, 11, 15, 16, 17, 18, 19, 20, 21, 22, 24, 25, 27, 28, 30, 31, 33, 34, 36, 39], "repres": [1, 4, 5, 7, 17, 35, 46], "sycl": [1, 2, 4, 5, 7, 8, 11, 15, 16, 17, 18, 28, 35, 36, 38, 39, 41, 44, 46], "prototyp": [1, 4, 5], "kernel": [1, 4, 5, 6, 8, 13, 16, 17, 19, 20, 21, 22, 23, 24, 25, 27, 28, 30, 31, 33, 34, 35, 36, 38, 40, 42], "befor": [1, 2, 4, 5, 11, 16, 19], "thei": [1, 5, 19, 30, 46], "ar": [1, 2, 4, 5, 8, 11, 14, 15, 16, 17, 19, 27, 28, 30, 32, 33, 35, 37, 39, 40, 43, 45, 46], "jit": [1, 5, 15, 23, 35, 45], "compil": [1, 3, 4, 5, 13, 15, 17, 18, 19, 23, 25, 28, 30, 36, 45], "atomicref": [1, 4], "analogu": [1, 4, 5, 42], "type": [1, 3, 4, 5, 8, 15, 16, 17, 26, 35, 37, 39], "an": [1, 2, 3, 4, 5, 6, 7, 8, 11, 15, 16, 17, 18, 20, 32, 33, 35, 37, 38, 39, 46], "atom": [1, 2, 4, 17, 19, 36, 39], "refer": [1, 4, 7, 11, 13, 15, 16, 17, 22, 23, 28, 30, 40, 45, 46], "i": [1, 2, 4, 6, 7, 8, 11, 14, 15, 16, 17, 19, 20, 21, 22, 24, 25, 27, 28, 29, 30, 31, 32, 33, 34, 35, 37, 38, 39, 40, 41, 42, 44, 45, 46], "ref": [1, 4], "index": [1, 4, 5, 8, 15, 30, 37, 39], "0": [1, 4, 7, 8, 11, 14, 15, 16, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 30, 33, 34, 35, 37, 38, 39, 40, 42, 46], "memory_ord": [1, 4, 7], "memoryord": [1, 4, 7], "relax": [1, 4, 7], "memory_scop": [1, 4], "memoryscop": [1, 2, 4, 7], "devic": [1, 4, 7, 11, 13, 15, 17, 18, 19, 35, 36, 37, 39, 40, 41, 46], "address_spac": [1, 4], "addressspac": [1, 4, 7], "global": [1, 4, 5, 7, 8, 17, 30, 39, 40, 44, 46], "view": [1, 4], "data": [1, 4, 8, 15, 17, 18, 23, 26, 28, 35, 36, 39, 40, 44], "can": [1, 4, 5, 8, 11, 14, 15, 16, 22, 23, 25, 28, 30, 32, 33, 35, 38, 39, 41, 42, 44, 45, 46], "updat": [1, 4, 17, 44], "us": [1, 2, 3, 4, 5, 13, 15, 16, 17, 21, 23, 25, 27, 28, 31, 32, 33, 35, 37, 38, 39, 40, 42, 44, 46], "ani": [1, 2, 4, 11, 16, 21, 40, 42, 43, 44, 46], "fetch_": [1, 4], "member": [1, 3, 4, 5, 7, 8], "fetch_add": [1, 4], "val": [1, 4, 37], "add": [1, 4, 15, 17, 32, 37, 42, 43], "operand": [1, 4], "object": [1, 2, 3, 4, 5, 6, 8, 15, 16, 17, 30, 35, 40, 44, 46], "referenc": [1, 4], "fetch_sub": [1, 4], "subtract": [1, 4, 37], "fetch_min": [1, 4], "calcul": [1, 4], "minimum": [1, 4, 17], "valu": [1, 3, 4, 7, 16, 17, 19, 20, 23, 24, 30, 31, 37, 38, 46], "fetch_max": [1, 4], "maximum": [1, 4], "fetch_and": [1, 4], "bitwis": [1, 4], "AND": [1, 4], "fetch_or": [1, 4], "OR": [1, 4], "fetch_xor": [1, 4], "xor": [1, 4], "load": [1, 4, 17, 25, 34, 37], "store": [1, 4, 16, 37, 42, 44, 46], "exchang": [1, 4], "replac": [1, 4, 17, 35], "compare_exchang": [1, 4], "expect": [1, 4], "desir": [1, 4], "expected_idx": [1, 4], "compar": [1, 4], "assign": [1, 4, 26, 29], "result": [1, 4, 16, 17, 20, 21, 22, 24, 27, 30, 31, 33, 34, 40, 42, 46], "return": [1, 3, 4, 5, 8, 15, 16, 17, 20, 21, 22, 24, 27, 30, 31, 33, 34, 35, 37, 38, 42, 44, 46], "origin": [1, 4, 5], "paramet": [1, 2, 4, 6, 8, 37, 45, 46], "ad": [1, 4, 15, 26, 38, 42], "The": [1, 2, 4, 5, 7, 8, 11, 15, 16, 17, 19, 21, 22, 23, 29, 30, 32, 33, 35, 37, 38, 39, 40, 43, 44, 46], "from": [1, 4, 13, 16, 17, 18, 19, 21, 23, 30, 32, 33, 35, 38, 40, 43, 45, 46], "against": [1, 4], "ANDed": [1, 4], "ORed": [1, 4], "xore": [1, 4], "If": [1, 4, 6, 16, 23, 25, 32, 46], "equal": [1, 4, 16, 30, 46], "otherwis": [1, 4], "arrai": [1, 4, 15, 16, 17, 18, 22, 24, 25, 27, 28, 30, 31, 33, 34, 35, 37, 40, 42, 43, 46], "offset": [1, 4], "where": [1, 4, 16, 21, 22, 30, 46], "present": [1, 4, 16, 21, 35, 37, 45], "true": [1, 4, 15, 16, 21, 22, 25, 27, 28, 30, 33, 34], "comparison": [1, 4], "oper": [1, 2, 4, 16, 17, 18, 36, 39, 43, 44, 46], "were": [1, 4, 16], "success": [1, 4], "simul": 2, "": [2, 4, 8, 15, 16, 17, 19, 28, 40, 45, 46], "primit": 2, "group_barri": [2, 4], "group": [2, 4, 5, 8, 32, 39, 40, 46], "fence_scop": [2, 4], "perform": [2, 4, 16, 17, 18, 37], "across": [2, 4, 16], "all": [2, 4, 5, 8, 11, 14, 16, 17, 28, 30, 32, 34, 35, 40, 44, 46], "work": [2, 4, 5, 8, 16, 17, 20, 25, 28, 29, 31, 32, 39, 40, 44, 45, 46], "item": [2, 4, 5, 8, 16, 39, 40, 44, 46], "index_space_id": [2, 4], "work_group": [2, 4, 7], "model": [2, 4, 13, 15, 17, 35, 39], "after": [2, 4, 11, 15, 16, 30], "It": [2, 4, 8, 11, 15, 16, 23, 30, 31, 39], "synchron": [2, 4, 36, 39], "within": [2, 4, 5, 11, 43], "must": [2, 4, 11, 16, 37, 46], "execut": [2, 4, 5, 8, 15, 16, 19, 23, 26, 28, 33, 35, 39, 41], "construct": [2, 4, 16, 39], "continu": [2, 4, 21, 22, 25, 28, 33, 34], "beyond": [2, 4, 16], "howev": [2, 4, 11, 38, 42], "unlik": [2, 4, 15, 38, 39], "implicitli": [2, 4, 16], "level": [2, 4, 15, 17, 18, 23, 26, 32, 38], "doe": [2, 4, 16, 21, 30, 38, 40, 41, 42], "allow": [2, 4, 15, 16, 17, 28, 33, 35, 37, 40], "specifi": [2, 4, 5, 8, 11, 13, 15, 17, 19, 22, 40, 46], "argument": [2, 4, 6, 11, 15, 16, 17, 20, 26, 27, 28, 34, 40, 44, 46], "sub_group_barri": [2, 4], "should": [2, 3, 4, 11, 16, 20, 22, 29, 32, 40, 42], "ha": [2, 4, 11, 15, 16, 20, 29, 33], "onli": [2, 4, 15, 16, 17, 38, 39, 44, 45, 46], "sub": [2, 4, 15, 37, 43], "mem": [2, 4, 40], "fenc": [2, 4, 40, 44], "ensur": [2, 4, 11, 16, 23, 33, 41, 44], "memori": [2, 4, 7, 16, 17, 28, 40, 44], "access": [2, 4, 11, 16, 17, 31, 41, 46], "issu": [2, 4, 11, 13, 16, 17, 20, 28, 29], "re": [2, 4, 17, 37], "order": [2, 4, 7, 19, 44], "those": [2, 4, 19, 37], "g": [2, 4, 16, 23, 32], "releas": [2, 4, 7, 11, 13, 32, 42], "prior": [2, 4], "acquir": [2, 4, 7], "afterward": [2, 4], "implicit": [2, 4, 16], "provid": [2, 3, 4, 5, 10, 11, 15, 16, 17, 18, 19, 26, 30, 31, 35, 37, 38, 41, 42, 44, 45], "explicit": [2, 4], "option": [2, 4, 13, 15, 17, 23, 25, 32, 36, 44, 46], "scope": [2, 4, 7, 30], "consist": [2, 4, 7, 8, 17], "flagenum": [3, 4, 7], "help": [3, 17], "distinguish": 3, "intenum": 3, "intend": 3, "integ": [3, 4, 7, 17], "liter": [3, 30], "insid": [3, 13, 17, 23, 28, 36, 39, 40, 46], "infer": [3, 16, 17, 35, 45], "infrastructur": 3, "helper": [3, 16, 17, 44], "consid": [3, 16, 21, 22, 33], "base": [3, 4, 7, 8, 11, 15, 16, 17, 32], "enum": [3, 4, 7], "numba": [3, 10, 11, 14, 15, 18, 20, 22, 23, 24, 25, 26, 27, 28, 34, 35, 36, 37, 38, 39, 40, 41, 42, 44], "basetyp": 3, "dummi": [3, 30], "int": [3, 4, 5, 8, 30, 37, 42, 43, 46], "classmethod": 3, "instanc": [3, 4, 5, 6, 16, 46], "modul": [4, 15, 17, 30, 39], "set": [4, 8, 11, 15, 17, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 30, 31, 34, 35, 41, 43, 44, 45], "analog": [4, 37, 45], "c": [4, 11, 15, 16, 17, 18, 21, 22, 25, 27, 28, 30, 33, 34, 35, 40, 46], "api": [4, 11, 13, 15, 16, 17, 18, 20, 24, 27, 30, 31, 34, 38, 40], "meant": [4, 11, 46], "like": [4, 11, 17, 18, 31, 33, 38, 45, 46], "pure": 4, "them": 4, "atomic_ref": 4, "barrier": [4, 40, 42, 44], "flag_enum": [4, 7], "launcher": 4, "memory_enum": 4, "rang": [4, 5, 6, 15, 16, 17, 21, 22, 25, 27, 28, 30, 33, 34, 36, 37, 40, 42, 43, 46], "identifi": [4, 5, 40], "nditem": [4, 5], "nd_item": [4, 5], "address": [4, 7, 17, 36, 39, 45], "space": [4, 7, 8, 16, 17, 36, 39], "support": [4, 7, 11, 15, 16, 17, 18, 19, 28, 29, 34, 35, 36, 39, 44, 45, 46], "enumer": [4, 7, 46], "dpcpp": [4, 7, 11, 17], "For": [4, 7, 11, 16, 19, 20, 23, 28, 29, 32, 44, 46], "more": [4, 7, 15, 16, 23, 33, 46], "detail": [4, 7, 15, 16, 30, 32, 45], "pleas": [4, 7, 11, 15, 46], "ndrang": [4, 5, 6, 8, 17, 40, 42, 46], "A": [4, 5, 6, 7, 8, 11, 16, 17, 19, 22, 40, 42, 46], "encapsul": [4, 8], "launch": [4, 6, 8, 16, 17, 25, 46], "structur": [4, 8], "singl": [4, 8, 16, 17, 23, 33], "call_kernel": [4, 6], "kernel_fn": [4, 6], "index_rang": [4, 6], "kernel_arg": [4, 6], "over": [4, 6, 16, 17, 35], "either": [4, 6, 11, 16, 43, 44], "global_rang": [4, 5, 8, 40], "local_rang": [4, 5, 8, 40], "group_rang": [4, 5], "list": [4, 5, 11, 13, 16, 19, 34, 43, 46], "get_group_id": [4, 5, 42, 46], "dim": [4, 5], "nd": [4, 5, 16], "get_group_linear_id": [4, 5], "linear": [4, 5], "version": [4, 5, 11, 27, 31, 32, 39], "get_group_rang": [4, 5], "extent": [4, 5], "number": [4, 5, 8, 16, 22, 39, 46], "get_group_linear_rang": [4, 5], "total": [4, 5, 39, 42, 46], "nd_rang": [4, 5, 8], "get_local_rang": [4, 5, 8], "dimens": [4, 5, 8, 35, 39], "get_local_linear_rang": [4, 5], "sinc": [4, 5, 16, 30], "have": [4, 5, 16, 22, 38], "defin": [4, 5, 8, 19, 22, 39], "posit": [4, 5, 6], "id": [4, 5, 16, 32], "along": [4, 5, 8, 11], "local": [4, 5, 7, 11, 16, 17, 25, 26, 28, 32, 39, 40, 42, 44, 46], "uniqu": [4, 5], "mai": [4, 5, 11, 15, 16, 23, 28, 30, 33, 34, 40], "been": [4, 5], "programm": [4, 5], "chosen": [4, 5], "runtim": [4, 5, 11, 15, 16, 17, 32], "each": [4, 5, 8, 19, 28, 39, 40, 42], "point": [4, 5, 16, 17, 18, 19, 22, 35, 44, 46], "get_linear_id": [4, 5], "get": [4, 5, 8, 13, 15, 16, 31, 32, 46], "associ": [4, 5, 16], "get_id": [4, 5], "idx": [4, 5, 37, 46], "specif": [4, 5, 7, 16, 17, 38, 42], "get_rang": [4, 5], "size": [4, 5, 8, 16, 19, 35, 39, 40, 42, 46], "could": [4, 5, 16, 30, 46], "found": [4, 5, 11, 14, 42, 45], "item_bas": [4, 5], "global_item": [4, 5], "local_item": [4, 5], "get_global_id": [4, 5, 15, 16, 21, 22, 25, 27, 28, 30, 33, 34, 38, 40, 42, 46], "get_global_linear_id": [4, 5], "get_local_id": [4, 5, 42, 46], "get_local_linear_id": [4, 5], "get_global_rang": [4, 5, 8], "get_group": [4, 5], "privat": [4, 7, 17, 40], "constant": [4, 7], "2": [4, 7, 8, 14, 20, 21, 22, 24, 25, 27, 28, 31, 33, 34, 35, 38, 39, 40], "3": [4, 7, 8, 16, 20, 21, 22, 24, 27, 28, 31, 33], "4": [4, 7, 8, 24, 39, 40], "kept": [4, 7], "correspond": [4, 7], "consume_unsupport": [4, 7], "acq_rel": [4, 7], "seq_cst": [4, 7], "5": [4, 7, 16, 17, 20, 24, 27, 30, 31, 34], "2020": [4, 7, 8, 40], "section": [4, 7, 8, 21, 23, 42], "8": [4, 7, 17, 24, 27, 30, 32, 39], "work_item": [4, 7], "sub_group": [4, 7], "system": [4, 7, 16, 32], "global_s": [4, 8, 21, 22, 25, 27, 28, 30, 33, 34, 40, 42, 46], "local_s": [4, 8, 46], "well": [4, 8, 11, 16], "pass": [4, 8, 11, 15, 16, 17, 19, 30, 40, 44, 46], "parallel_for": [4, 8, 16], "basic": [4, 8, 13, 15, 28, 36], "two": [4, 8, 17, 21, 42, 44, 46], "one": [4, 8, 11, 16, 17, 42, 46], "other": [4, 8, 11, 15, 17, 21, 26, 40], "mimic": [4, 8], "behavior": [4, 8, 23, 32, 33], "tupl": [4, 8, 43], "abstract": [4, 8], "describ": [4, 8, 16], "element": [4, 8, 16, 24, 37, 42], "buffer": [4, 8, 16, 44], "depend": [4, 8, 11, 16, 17, 23], "dimension": [4, 8, 42, 46], "just": [4, 8, 18], "wrapper": [4, 8], "top": [4, 8, 11, 35, 39], "three": [4, 8, 15, 16, 30, 40], "undefined_dimens": [4, 8], "e": [4, 8, 16, 17, 18, 23, 30, 38, 40], "multipli": [4, 8], "individu": [4, 8, 23], "callabl": [4, 6], "rais": [4, 6, 16, 37, 43], "valueerror": [4, 6], "first": [4, 6, 11, 15, 16, 21, 23, 31, 32, 33, 37], "second": [4, 6, 16, 21], "collect": 7, "syntact": 7, "design": [8, 15], "line": [8, 17, 22, 23, 30, 31, 33], "spec": 8, "9": [8, 17, 24], "dpex": [10, 11, 13, 14, 15, 17, 20, 21, 22, 24, 25, 26, 27, 28, 29, 30, 31, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 44, 45], "instruct": [10, 18, 33], "dpbench": 10, "sampl": [10, 16, 28, 30, 41], "its": [11, 16, 17, 24, 44], "recommend": [11, 17, 23, 30], "anaconda": [11, 15], "org": 11, "intel": [11, 13, 15, 17, 18, 21, 25, 26, 32, 36, 39, 40], "channel": [11, 17], "latest": [11, 17, 25, 32], "product": [11, 17, 28], "n": [11, 16, 22, 25, 27, 28, 30, 33, 34, 35, 37, 40, 46], "env": [11, 17, 23, 25], "dpnp": [11, 13, 15, 17, 21, 22, 25, 27, 28, 30, 33, 34, 36, 40, 41, 46], "dpctl": [11, 16, 17, 22, 25, 27, 28, 30, 33, 34, 35, 40, 45], "llvm": [11, 17, 19, 26], "spirv": [11, 17, 19], "forg": 11, "To": [11, 15, 16, 20, 23, 24, 28, 32, 33, 34, 38, 41], "try": [11, 30, 43], "out": [11, 16, 23, 28, 30], "bleed": 11, "edg": 11, "tip": [11, 13, 28], "main": [11, 13, 17, 37, 40, 46], "trunk": 11, "dppy": 11, "label": [11, 30], "dev": [11, 16, 17, 25, 32], "setuptool": 11, "scikit": [11, 17], "backend": [11, 37], "step": [11, 16, 17, 23, 26, 28, 30], "environ": [11, 15, 17, 19, 20, 23, 24, 28, 30, 32, 34], "new": [11, 15, 17], "activ": [11, 19, 23, 25, 32], "vendor": [11, 16, 18, 32, 39], "recip": [11, 17], "setup": [11, 17], "py": [11, 17, 19, 20, 21, 22, 24, 25, 27, 28, 30, 31, 33, 34, 37, 42, 45], "As": [11, 15, 30], "necessari": 11, "suggest": 11, "hass": 11, "need": [11, 15, 16, 19, 32, 38, 40, 46], "cmake": 11, "llvmdev": [11, 17], "pytest": [11, 17], "clone": 11, "repositori": 11, "git": [11, 17], "http": [11, 17], "github": [11, 15, 16, 17, 32], "com": [11, 17], "intelpython": [11, 17], "cd": [11, 32], "develop": [11, 16, 17], "dockerfil": [11, 17], "direct": [11, 28], "user": [11, 15, 16, 17, 19, 32, 38, 40], "bundl": 11, "also": [11, 15, 16, 20, 21, 22, 23, 32, 33, 35, 39], "driver": [11, 17, 23, 25, 28, 40, 46], "librari": [11, 15, 16, 18, 25, 34, 35, 39], "ship": 11, "multistag": 11, "which": [11, 16, 17, 30, 33, 37, 39, 44, 45], "mean": [11, 17, 30, 39], "differ": [11, 15, 16, 18, 19, 23, 30, 32, 33, 39], "target": [11, 13, 15, 17, 18, 30, 39, 45], "avail": [11, 13, 15, 17, 19, 30], "most": [11, 23, 35], "ones": [11, 15, 17, 35], "gpu": [11, 15, 16, 17, 32, 35, 41, 46], "builder": [11, 17], "t": [11, 17], "run": [11, 17, 20, 21, 22, 24, 25, 27, 28, 30, 31, 33, 34, 46], "rm": 11, "when": [11, 15, 16, 17, 30, 31, 44], "attempt": [11, 16], "relat": [11, 17], "call": [11, 16, 17, 30, 35, 39, 44, 46], "limit": [11, 20, 36, 38, 45], "bypass": 11, "valid": [11, 17, 19], "credenti": 11, "github_us": 11, "github_password": 11, "arg": [11, 25, 26, 30, 35, 46], "increas": [11, 17, 28], "token": 11, "instead": [11, 16, 17, 23], "password": 11, "behind": [11, 16], "firewal": 11, "proxi": 11, "server": 11, "http_proxi": 11, "https_proxi": 11, "These": 11, "lowercas": 11, "via": [11, 17, 23, 41], "python_vers": 11, "By": 11, "default": [11, 15, 17, 19, 23, 30, 32, 33, 40], "offici": 11, "slim": 11, "debian": 11, "request": [11, 13, 17], "base_imag": 11, "custom": [11, 17, 32], "note": [11, 16, 27], "ubuntu": [11, 17, 32], "follow": [11, 13, 15, 17, 19, 21, 22, 23, 25, 26, 28, 29, 30, 31, 32, 33, 34, 35, 37, 43, 46], "see": [11, 20, 21, 22, 23, 24, 25, 27, 28, 29, 30, 31, 32, 33, 34], "current": [11, 15, 23, 33, 39, 46], "cr_tag": 11, "igc_tag": 11, "cm_tag": 11, "l0_tag": 11, "oneapi_vers": 11, "dpctl_git_branch": 11, "dpctl_git_url": 11, "dpnp_git_branch": 11, "dpnp_git_url": 11, "numba_dpex_git_branch": 11, "numba_dpex_git_url": 11, "cmake_vers": 11, "cmake_version_build": 11, "intel_numpy_vers": 11, "intel_numba_vers": 11, "cython_vers": 11, "scikit_build_vers": 11, "There": [11, 39], "sever": [11, 15, 22, 30, 35], "alreadi": 11, "ideal": 11, "quickli": 11, "ghcr": 11, "io": [11, 17], "numba_dpex_vers": 11, "requir": [11, 17, 19, 24, 27, 32, 36, 42, 45], "stage": 11, "primarili": 11, "up": [11, 17, 28], "snippet": [11, 35], "20": [11, 19, 22, 30, 34], "py3": 11, "10": [11, 16, 20, 21, 22, 24, 25, 27, 28, 30, 31, 33, 34, 35, 37, 40], "bash": 11, "advis": [11, 16], "verifi": 11, "l": [11, 32, 46], "m": [11, 35], "f": 11, "enabl": [11, 17, 19, 23, 28, 31], "linux": [11, 17, 32], "dri": [11, 32], "you": [11, 16, 18, 22, 23, 25, 28, 30, 32, 33, 39, 46], "wsl": 11, "dxg": 11, "v": [11, 15, 17], "usr": [11, 32], "lib": [11, 17, 32], "unit": [11, 13, 16, 17, 39], "show": [11, 30, 35], "wai": [11, 15, 18, 22, 39], "pyarg": 11, "how": [11, 16, 18, 21, 39], "featur": [13, 16, 17, 23, 36, 39], "start": [13, 15, 17, 23, 32, 46], "instal": [13, 15, 17, 23, 25, 32], "pre": [13, 17], "built": [13, 17, 30, 35, 39], "conda": [13, 17, 25], "packag": [13, 15, 16, 17], "build": [13, 17], "sourc": [13, 15, 17, 20, 22, 24, 25, 27, 30, 31, 33, 34], "docker": [13, 15], "test": [13, 17, 27, 30, 31, 40, 46], "exampl": [13, 15, 16, 17, 19, 21, 22, 25, 33, 35, 36, 39, 40, 41, 44, 46], "program": [13, 17, 18, 19, 21, 22, 23, 33, 35, 36, 44, 46], "recogn": 13, "offload": [13, 15, 17, 19, 36, 39], "share": [13, 17, 25, 34, 40], "comput": [13, 15, 17, 18, 32, 35, 42, 46], "tutori": 13, "statement": [13, 36, 43], "debug": [13, 17, 19, 20, 21, 22, 24, 26, 27, 33, 34, 36, 41], "distribut": [13, 15, 17, 21, 25, 26, 32, 36], "gdb": [13, 17, 20, 21, 22, 23, 24, 25, 26, 27, 30, 31, 32, 33, 34, 36], "configur": [13, 17, 23, 28, 30, 33, 36], "link": [13, 17, 32], "contribut": [13, 14], "guid": [13, 17, 32], "classif": 13, "cycl": 13, "pull": [13, 17], "code": [13, 15, 16, 17, 18, 20, 22, 23, 24, 27, 28, 30, 31, 33, 34, 35, 39, 41, 46], "guidelin": 13, "benchmark": 13, "jupyt": 13, "notebook": 13, "glossari": 13, "licens": [13, 17, 40], "changelog": 13, "under": [14, 16], "apach": [14, 17, 40], "usag": [14, 17, 35, 36, 37, 39, 40], "project": [14, 15, 17], "subject": 14, "term": [14, 39], "condit": [14, 17, 22, 25, 26, 28, 30, 33, 34], "parallel": [15, 16, 18, 36, 39, 40], "extens": [15, 16, 17, 18, 19, 35, 39, 46], "architectur": [15, 16], "agnost": [15, 39], "front": 15, "end": [15, 16, 30, 32, 46], "numpi": [15, 16, 17, 18, 35, 39, 40, 41, 45, 46], "languag": [15, 19], "open": 15, "part": [15, 28, 39, 42], "ai": 15, "analyt": 15, "toolkit": 15, "cloud": 15, "imag": [15, 44], "learn": [15, 46], "similar": [15, 39, 46], "cuda": [15, 37, 39, 42, 44, 45], "dpc": [15, 16, 18, 37], "spir": [15, 17], "opencl": [15, 17, 18, 32, 39], "oneapi": [15, 16, 17, 20, 21, 22, 24, 25, 27, 28, 30, 31, 32, 33, 34], "zero": [15, 17, 23, 27, 30, 32, 35, 37, 40, 42], "cpu": [15, 16, 18, 28, 46], "In": [15, 16, 18, 19, 25, 27, 31, 39, 40, 42, 46], "futur": [15, 25, 42], "hardwar": [15, 18, 39], "illustr": 15, "vector": [15, 17, 35, 39, 40, 46], "addit": [15, 17, 33, 37, 42], "written": [15, 42, 46], "import": [15, 16, 17, 21, 22, 25, 27, 28, 30, 33, 34, 35, 40, 46], "def": [15, 16, 20, 21, 22, 24, 25, 27, 28, 30, 31, 33, 34, 35, 37, 38, 40, 42, 46], "vecadd_kernel": 15, "b": [15, 20, 21, 22, 24, 25, 27, 28, 30, 33, 34, 38, 40, 46], "1024": [15, 35], "empty_lik": [15, 16, 17, 21, 22, 33, 35], "print": [15, 17, 20, 21, 22, 25, 26, 27, 28, 30, 31, 33, 34, 35, 37, 40, 46], "abov": 15, "alloc": [15, 16, 17, 40], "input": [15, 16, 17, 35, 46], "subsequ": 15, "determin": [15, 16, 46], "standard": [15, 16, 18, 39], "chang": [15, 32], "keyword": [15, 16, 17], "possibl": [15, 16, 17, 23, 30, 31], "leav": 15, "undefin": 15, "let": [15, 16], "select": [15, 16], "flag": [15, 17, 19], "further": 15, "extend": [15, 17, 26, 30], "njit": [15, 17], "equival": [15, 16, 23, 44], "addition": 15, "prang": [15, 17, 35], "loop": [15, 17, 35, 42], "express": [15, 17, 20, 34, 35, 39], "ndarrai": [15, 17, 35], "convert": [15, 17], "same": [15, 16, 18, 44], "exist": [15, 16, 17], "refactor": [15, 17], "Such": [15, 16, 39, 42], "region": [15, 40], "parallelli": 15, "depict": 15, "vecadd_v1": 15, "vecadd_v2": 15, "vecadd_v3": 15, "shape": [15, 24, 34, 35, 40, 46], "invok": [15, 21, 38, 42, 44, 45], "user_manu": 15, "dpnp_offload": 15, "heterogen": [16, 18], "multipl": [16, 17, 23, 33, 39, 42], "want": [16, 25, 32, 44, 46], "engag": 16, "common": [16, 17, 28], "consum": 16, "grade": 16, "laptop": 16, "integr": [16, 17, 41], "discret": 16, "alongsid": 16, "har": 16, "power": [16, 42], "know": 16, "answer": 16, "kei": [16, 32], "question": 16, "workload": 16, "applic": [16, 17, 23, 28], "manag": [16, 18, 43], "known": [16, 39], "underli": 16, "get_devic": 16, "interest": 16, "select_gpu_devic": 16, "filter": [16, 17], "selector": 16, "string": [16, 17], "sycldevic": 16, "constructor": [16, 17, 35], "dev_gpu": 16, "dev_cpu": 16, "stand": 16, "alon": 16, "gpu_selector": 16, "select_devic": 16, "dev_gpu_alt": 16, "cpu_selector": 16, "dev_cpu_alt": 16, "select_cpu_devic": 16, "queri": 16, "properi": 16, "name": [16, 17, 22, 25, 30, 40], "maxim": 16, "etc": [16, 32], "we": [16, 37, 42], "digress": 16, "explain": 16, "queue": [16, 17, 39, 44], "unifi": 16, "bring": 16, "portabl": [16, 18, 39], "anoth": [16, 38, 45], "aspect": [16, 19], "inher": 16, "flexibl": 16, "make": [16, 17, 22, 25, 31, 32], "go": [16, 17, 33], "even": 16, "strive": 16, "techniqu": 16, "templat": 16, "metaprogram": 16, "dynam": 16, "polymorph": 16, "special": [16, 17, 38], "dispatch": [16, 17], "dure": [16, 17], "onemkl": [16, 35], "task": 16, "submit": [16, 39], "insert": [16, 30], "graph": 16, "onc": 16, "becom": 16, "whose": 16, "met": 16, "submiss": [16, 17], "therefor": 16, "alwai": [16, 27, 31], "directli": [16, 39], "indic": [16, 17], "q1": 16, "syclqueu": [16, 17, 35], "q2": 16, "nativ": [16, 17, 18, 19], "case": [16, 17, 21], "orchestr": 16, "evalu": [16, 20], "polynomi": 16, "everi": 16, "x": [16, 24, 30, 31, 32, 33, 34, 35, 46], "receiv": [16, 23, 33], "y": [16, 25], "np": [16, 17, 21, 22, 25, 27, 28, 30, 33, 34, 37, 40, 42], "p": 16, "onapi_ext": 16, "offloaded_poly_evalu": 16, "exec_q": 16, "appli": [16, 17], "doubl": [16, 34], "precis": [16, 17], "float": [16, 17, 18, 19, 30, 34, 43], "pointer": [16, 17], "translat": 16, "void": [16, 34], "cpp_offloaded_poly_evalu": 16, "q": [16, 20, 21, 22, 24, 25, 27, 28, 30, 31, 33, 34, 35], "const": [16, 30], "size_t": 16, "malloc": 16, "buf_x": 16, "buf_i": 16, "handler": 16, "cgh": 16, "accessor": 16, "flow": 16, "pattern": [16, 44], "acc_x": 16, "read_onli": 16, "acc_i": 16, "write_onli": 16, "no_init": 16, "lambda": 16, "accx": 16, "acci": 16, "wait": [16, 42, 44], "reader": 16, "excel": 16, "freeli": 16, "book": [16, 18], "our": [16, 17], "write": [16, 17, 18, 35, 36, 39, 42, 44], "numba_dpex_poli": 16, "done": [16, 21, 22, 25, 27, 28, 30, 32, 33, 34, 37, 40], "context": [16, 43], "random": [16, 17, 22, 25, 27, 28, 30, 33, 34, 40, 42], "randn": 16, "6": [16, 17, 24, 30, 39], "device_context": [16, 17, 45], "while": [16, 17, 42], "given": [16, 39, 42], "temporari": [16, 17], "thu": 16, "gpu_dev": 16, "wa": [16, 25], "u": 16, "precompil": 16, "__call__": 16, "method": [16, 17], "sure": 16, "conveni": 16, "interpret": 16, "come": 16, "cost": 16, "copi": [16, 17, 40, 46], "host": [16, 19, 32, 38, 46], "commenc": 16, "some": [16, 30, 37, 44], "back": 16, "complet": 16, "usm": [16, 17], "tensor": [16, 17, 18, 40], "usm_ndarrai": [16, 17], "conform": 16, "dpt": [16, 40, 42], "arang": [16, 21, 22, 33, 37, 40], "1e": [16, 17], "usm_typ": 16, "output": [16, 22, 23, 25, 30, 34, 35, 40, 46], "default_local_s": 16, "unambigu": 16, "both": [16, 46], "sycl_queu": [16, 35], "ambigu": [16, 17], "indeterminateexecutionqueueerror": 16, "explicitli": [16, 30, 42, 46], "migrat": 16, "accomplish": 16, "asarrai": 16, "target_devic": 16, "to_devic": 16, "asnumpi": [16, 40, 46], "automat": [16, 17], "deduct": 16, "consit": 16, "control": [16, 17, 18, 44], "full": [16, 17, 22, 23, 35, 39], "through": [16, 33], "creation": [16, 17], "mandat": 16, "obtain": [16, 46], "earlier": 16, "altern": 16, "readabl": 16, "rational": 16, "guarante": 16, "abl": [16, 39], "correctli": [16, 20, 29, 32], "derefer": 16, "involv": 16, "reus": [16, 17], "without": [16, 17, 23, 33, 34], "rule": 16, "prescrib": 16, "combin": 16, "stipul": 16, "measur": [16, 46], "schedul": [16, 23, 26], "unsam": 16, "except": [16, 17, 43], "sometim": 16, "do": [16, 17, 32], "effici": [16, 23, 33], "heavi": 16, "feel": 16, "free": [16, 18], "file": [16, 17, 19, 22, 25, 30, 32, 34], "reach": [16, 22, 44], "gitter": [16, 17], "encount": 16, "notabl": 17, "format": [17, 19], "keep": 17, "adher": 17, "semant": [17, 44], "dead": 17, "silenc": 17, "cover": 17, "error": [17, 28], "1163": 17, "pin": 17, "ci": 17, "1133": 17, "mangl": 17, "1112": 17, "1143": 17, "initi": 17, "scan": 17, "1128": 17, "1123": 17, "secur": 17, "polici": [17, 30], "1117": 17, "1107": 17, "1116": 17, "1127": 17, "1139": 17, "1140": 17, "renam": 17, "clearli": 17, "1145": 17, "dpnpndarrai": 17, "1118": 17, "1113": 17, "bug": 17, "1068": 17, "774": 17, "caus": [17, 28], "due": 17, "improp": 17, "emul": 17, "1103": 17, "1097": 17, "879": 17, "tool": 17, "1108": 17, "atomic_op": [17, 37], "cl": 17, "numba_dpex_activate_atomics_fp_n": 17, "improv": [17, 31], "overload": 17, "1083": 17, "reduct": [17, 35, 36, 37, 39], "1089": 17, "itanium": 17, "cxx": 17, "abi": 17, "mangler": 17, "1080": 17, "sourcewar": 17, "docstr": 17, "1081": 17, "typo": 17, "messag": 17, "interfac": 17, "1082": 17, "999": 17, "proper": 17, "box": 17, "unbox": 17, "dpjit": [17, 35], "decor": [17, 23, 35, 38, 42, 45], "963": 17, "1064": 17, "1032": 17, "991": 17, "full_lik": 17, "997": 17, "complex64": 17, "complex128": 17, "parfor": 17, "1033": 17, "1035": 17, "config": [17, 19], "constantsizestaticlocalmemorypass": [17, 19], "57": 17, "1030": 17, "1003": 17, "1002": 17, "1054": 17, "1056": 17, "1060": 17, "lower": 17, "happen": [17, 23, 33], "pipelin": [17, 19], "996": 17, "now": [17, 46], "monkei": 17, "patch": 17, "move": [17, 33], "numba_patch": 17, "redesign": 17, "suit": 17, "1018": 17, "1017": 17, "1015": 17, "1036": 17, "1037": 17, "1072": 17, "stride": [17, 24, 34, 42], "1023": 17, "cach": [17, 19], "946": 17, "mul": [17, 43], "1048": 17, "node": 17, "uhd": 17, "1074": 17, "1041": 17, "rename_numpy_functions_pass": 17, "stub": 17, "1025": 17, "1043": 17, "1049": 17, "llvm_spirv": 17, "path": [17, 25, 32], "979": 17, "manual": 17, "workflow": 17, "publish": 17, "repo": 17, "973": 17, "dtype": [17, 21, 22, 25, 27, 28, 30, 33, 34, 35, 37, 40, 42], "deriv": 17, "993": 17, "adjust": 17, "test_window": 17, "rt": 17, "990": 17, "layout": 17, "987": 17, "handl": [17, 43], "arraystruct": 17, "meminfo": [17, 24, 34], "null": 17, "close": [17, 45], "gh": 17, "965": 17, "972": 17, "887": 17, "902": 17, "dpextarget": 17, "empti": [17, 35], "zeros_lik": 17, "ones_lik": [17, 22, 25, 27, 28, 30, 33, 34, 40], "928": 17, "923": 17, "style": 17, "957": 17, "70": 17, "ufunc": [17, 45], "backport": 17, "split": [17, 39], "upstream": 17, "949": 17, "alias": 17, "851": 17, "alia": 17, "lru": 17, "804": 17, "func": [17, 21, 22, 30, 33, 38], "877": 17, "syntax": [17, 34, 46], "888": 17, "pacth": 17, "56": [17, 24, 34], "954": 17, "numba_dpex_dump_kernel_llvm": 17, "dump": [17, 19], "ir": [17, 19, 26, 31], "924": 17, "badg": 17, "chatroom": 17, "919": 17, "small": [17, 39], "script": 17, "copyright": 17, "header": 17, "917": 17, "dpexrt_python": 17, "nrt_meminfo": 17, "demonstr": [17, 35, 40, 42], "826": 17, "clk_global_mem_f": 17, "clk_local_mem_f": 17, "global_mem_f": [17, 44], "local_mem_f": [17, 40, 42, 44], "844": 17, "switch": [17, 19, 21, 33], "836": 17, "usmndarraytyp": 17, "usmndarrai": 17, "typess": 17, "880": 17, "intern": 17, "__sycl_usm_array_interface__": 17, "protocol": 17, "885": 17, "dpexcontext": 17, "dpextypingcontext": 17, "dpexkerneltarget": 17, "dpexkerneltypingcontext": 17, "dpnp_stubs_impl": 17, "953": 17, "mismatch": 17, "warn": 17, "importerror": 17, "925": 17, "827": 17, "858": 17, "linter": 17, "black": 17, "23": [17, 22, 27, 28, 30, 33], "isort": 17, "900": 17, "match": [17, 34, 37], "actual": 17, "904": 17, "rewrit": 17, "regress": 17, "912": 17, "896": 17, "qualnam": 17, "905": 17, "numpy_usm_shar": 17, "841": 17, "llvmlite": 17, "llvmpy": 17, "932": 17, "numba0": 17, "818": 17, "dpnp0": 17, "dpctl0": 17, "798": 17, "crash": 17, "take": [17, 35], "non": [17, 23], "771": 17, "pairwise_dist": [17, 35, 46], "machin": [17, 28, 33], "fp64": 17, "hw": 17, "806": 17, "728": 17, "coverag": 17, "action": 17, "upload": 17, "coveral": 17, "621": 17, "80": 17, "char": 17, "reformat": 17, "631": 17, "ignor": 17, "blame": 17, "632": 17, "numba_support": 17, "numba_vers": 17, "656": 17, "skip_no_numba055": 17, "662": 17, "parameter": 17, "661": 17, "skip_no_opencl_xpu": 17, "skip": [17, 33], "663": 17, "unsupport": [17, 39], "664": 17, "attribut": 17, "629": 17, "640": 17, "665": 17, "669": 17, "598": 17, "filter_str": 17, "miss": 17, "672": 17, "check": [17, 23, 25], "mkl": 17, "648": 17, "codeown": 17, "review": 17, "process": [17, 39], "670": 17, "skip_no_dpnp": 17, "668": 17, "675": 17, "644": 17, "680": 17, "forc": [17, 44], "681": 17, "682": 17, "adopt": 17, "55": [17, 24, 26, 27, 28, 30], "654": 17, "public": [17, 32], "695": 17, "708": 17, "709": 17, "710": 17, "659": 17, "674": 17, "prioriti": 17, "691": 17, "codestyl": 17, "696": 17, "697": 17, "libdpctlsyclinterfac": 17, "so": [17, 23, 30, 32, 33], "707": 17, "search": 17, "703": 17, "712": 17, "pokhodenkosa": 17, "cherri": 17, "pick": 17, "649": 17, "651": 17, "deveice_context": 17, "630": 17, "branch": 17, "610": 17, "deprecationwarn": 17, "pars": 17, "639": 17, "642": 17, "bin": 17, "window": 17, "626": 17, "627": 17, "clang": 17, "icx": 17, "622": 17, "574": 17, "numba_dppy_debug": 17, "578": 17, "preliminari": 17, "master": 17, "583": 17, "pr": 17, "586": 17, "trigger": 17, "tag": 17, "589": 17, "593": 17, "595": 17, "599": 17, "documenat": 17, "land": 17, "diptorupd": 17, "601": 17, "clean": 17, "readm": 17, "604": 17, "restrict": 17, "590": 17, "596": 17, "unskip": 17, "0rc1": 17, "606": 17, "infra": 17, "544": 17, "doc": 17, "about": [17, 26, 28, 46], "variabl": [17, 19, 23, 24, 25, 26, 27, 28, 29, 31, 32, 34, 44], "lifetim": [17, 26, 31], "534": 17, "536": 17, "558": 17, "info": [17, 19, 26], "543": 17, "561": 17, "cov": 17, "xdist": 17, "562": 17, "547": 17, "566": 17, "transform": 17, "command": [17, 21, 22, 24, 28, 30, 31, 32, 33, 34], "568": 17, "524": 17, "dot": 17, "matmul": 17, "565": 17, "older": 17, "backward": 17, "compat": [17, 45], "549": 17, "535": 17, "memcpi": 17, "async": 17, "529": 17, "532": 17, "523": 17, "matrix": [17, 35], "560": 17, "yml": 17, "550": 17, "delet": [17, 30], "unus": 17, "run_test": 17, "sh": [17, 25], "522": 17, "redund": 17, "521": 17, "introduc": [17, 39], "ultilit": 17, "489": 17, "505": 17, "508": 17, "507": 17, "509": 17, "497": 17, "510": 17, "54": 17, "493": 17, "514": 17, "7": [17, 21, 22, 24, 25, 27, 28, 30, 33], "513": 17, "502": 17, "515": 17, "dependeci": 17, "498": 17, "genreat": 17, "dwarf": 17, "symbol": [17, 26, 28], "500": 17, "emiss": [17, 28], "inform": [17, 23, 26, 28], "424": 17, "numba_dppi": 17, "455": 17, "cast": [17, 30], "432": 17, "assert": [17, 43], "466": 17, "opt": 17, "bitcod": 17, "481": 17, "426": 17, "numba_dppy_debuginfo": 17, "460": 17, "nest": [17, 26, 33], "breakpoint": [17, 20, 21, 24, 25, 26, 27, 28, 30, 33, 34], "434": 17, "variou": [17, 30, 35], "479": 17, "474": 17, "475": 17, "480": 17, "477": 17, "468": 17, "450": 17, "463": 17, "421": 17, "eager": 17, "291": 17, "op": 17, "435": 17, "deter": 17, "476": 17, "oneapi_root": [17, 25], "dir": 17, "411": 17, "unquot": 17, "386": 17, "408": 17, "378": 17, "388": 17, "389": 17, "380": 17, "323": 17, "394": 17, "400": 17, "402": 17, "396": 17, "405": 17, "362": 17, "379": 17, "cython": 17, "305": 17, "403": 17, "391": 17, "report": 17, "368": 17, "359": 17, "util": [17, 40, 46], "355": 17, "fail": [17, 23], "353": 17, "cpointer": 17, "339": 17, "optim": [17, 23, 26], "62": 17, "337": 17, "297": 17, "bandit": 17, "264": 17, "375": 17, "53": 17, "279": 17, "inlud": 17, "overrid": 17, "get_ufunc_info": 17, "dppytargetcontext": 17, "367": 17, "374": 17, "cpp": 17, "dpnp_glue": 17, "351": 17, "automerg": 17, "gold": 17, "349": 17, "347": 17, "wih": 17, "309": 17, "344": 17, "340": 17, "334": 17, "333": 17, "correct": [17, 25, 31, 40, 44], "310": 17, "303": 17, "350": 17, "blackschol": 17, "377": 17, "dppy_rt": 17, "393": 17, "390": 17, "346": 17, "leak": 17, "369": 17, "354": 17, "commit": 17, "345": 17, "tabl": [17, 26, 28], "smaller": 17, "308": 17, "306": 17, "subprocess": 17, "check_cal": 17, "269": 17, "modifi": [17, 20, 28], "cc": 17, "dparrai": 17, "linalg": 17, "transcendent": 17, "wheel": 17, "find": 17, "formatt": 17, "52": 17, "don": 17, "incorrect": 17, "standalon": 17, "diagnost": [17, 19], "fallback": 17, "eig": 17, "sum": [17, 37, 40, 42, 46], "max": [17, 42], "min": 17, "pseudo": 17, "site": 17, "till": 17, "gain": 17, "overlaod": 17, "oppos": 17, "previou": [17, 27, 31], "lower_builtin": 17, "dppl": 17, "dppltestcas": 17, "unittest": 17, "testcas": 17, "numba_dppy_": 17, "numba_dppy_save_ir_fil": 17, "numba_dppy_spirv_v": 17, "folder": 17, "No": [17, 25, 27, 30, 31], "cffi": 17, "old": [17, 37], "backup": 17, "includ": 17, "advisor": [17, 18], "profil": [17, 18], "descript": 18, "interchang": 18, "between": [18, 42], "vtune": 18, "analysi": 18, "bottleneck": 18, "leve": 18, "down": 18, "low": 18, "analyz": 18, "advic": 18, "better": 18, "composit": 18, "algorithm": [18, 41], "framework": 18, "ieee": 18, "754": 18, "2019": 18, "arithmet": 18, "essenti": 18, "robust": 18, "numer": 18, "foundat": 18, "conjunct": 18, "time": [18, 27, 30, 32, 42, 46], "mostli": 19, "inherit": 19, "core": 19, "disabl": [19, 23, 28], "prefix": 19, "append": [19, 46], "turn": [19, 23], "save_ir_fil": 19, "numba_dpex_save_ir_fil": 19, "numba_dpex_program": 19, "save": 19, "intermedi": 19, "represent": 19, "spirv_val": 19, "offload_diagnost": 19, "native_fp_atom": 19, "fp": 19, "atomci": 19, "emit": [19, 23], "debuginfo_default": 19, "dump_kernel_llvm": 19, "assembli": 19, "ll": 19, "dump_optim": 19, "enable_cach": 19, "numba_dpex_enable_cach": 19, "off": [19, 23], "cache_s": 19, "debug_cach": 19, "cahc": 19, "mechan": 19, "static_local_mem_pass": 19, "side": [20, 24, 27, 30, 31, 34], "common_loop_bodi": [20, 24, 27, 30, 31, 34], "param_a": [20, 24, 27, 30, 31, 34], "param_b": [20, 24, 27, 30, 31, 34], "param_c": [20, 24, 27, 30, 31, 34], "here": [20, 24, 27, 30, 31, 34, 46], "param_d": [20, 24, 27, 30, 31, 34], "session": [20, 24, 27, 30, 34], "numba_opt": [20, 21, 22, 23, 24, 27, 28, 30, 31, 33, 34], "numba_extend_variable_lifetim": [20, 24, 26, 34], "break": [20, 21, 24, 25, 26, 27, 28, 30, 31, 33, 34], "29": [20, 21, 24, 30, 33, 34], "thread": [20, 21, 22, 23, 24, 25, 27, 28, 30, 31, 33, 34, 40, 44], "hit": [20, 21, 22, 24, 25, 27, 28, 30, 31, 33, 34], "simd": [20, 21, 22, 24, 25, 27, 28, 30, 31, 33, 34], "lane": [20, 21, 22, 24, 25, 27, 28, 30, 31, 33, 34], "__main__": [20, 21, 22, 24, 25, 27, 28, 30, 31, 33, 34, 40], "15": [20, 32], "200": 20, "displai": [21, 24, 26], "summari": 21, "your": [21, 22, 32, 46], "got": 21, "simple_dpex_func": [21, 22, 33], "ndpx": [21, 22, 25, 27, 28, 30, 33, 34, 37, 38, 40, 42, 46], "func_sum": [21, 22, 33], "a_in_func": [21, 22, 33], "b_in_func": [21, 22, 33], "locat": [21, 22, 25, 28, 33, 34, 37], "kernel_sum": [21, 22, 33], "a_in_kernel": [21, 22, 33], "b_in_kernel": [21, 22, 33], "c_in_kernel": [21, 22, 33], "float32": [21, 22, 25, 27, 28, 30, 33, 34, 37, 40], "numa_dpex": 21, "pend": [21, 22, 25, 27, 28, 30, 33, 34], "28": [21, 30], "1073742080": [21, 33], "22": [21, 22, 25, 27, 28, 30, 33, 34], "stop": 22, "whenev": 22, "certain": 22, "place": 22, "simple_sum": [22, 25, 28, 33, 34], "data_parallel_sum": [22, 25, 27, 28, 30, 33, 34], "debugg": [22, 25, 27, 28, 30, 32, 33], "intelgt": 23, "gdbserver": 23, "gt": [23, 43], "igfxdcd": [23, 32], "intelgt_auto_attach_dis": 23, "attach": 23, "companion": [23, 28], "dcd": [23, 28], "heavili": 23, "At": [23, 34], "o3": 23, "export": [23, 25, 28, 32], "mode": [23, 28], "numba_dpex_debuginfo": [23, 28], "fals": 23, "numba_debuginfo": 23, "becaus": [23, 33], "multi": [23, 33, 44], "event": [23, 33], "interfer": [23, 33], "lock": [23, 26], "l1": [24, 27, 30, 34], "5931931659579277": [24, 27, 30], "l2": [24, 27, 30], "22954882979393004": [24, 30], "ptype": [24, 26, 31], "byte": [24, 34], "higher": [24, 27, 30, 32], "0x0": 24, "parent": [24, 34], "nitem": [24, 34], "items": [24, 34], "0x555558461000": 24, "10f": [24, 31], "0x555558461010": 24, "0x555558461020": 24, "var": [25, 30], "neo": [25, 28], "successfulli": 25, "least": [26, 34], "filenam": 26, "linenumb": 26, "cond": 26, "stepi": 26, "next": [26, 27, 28, 30, 35], "frame": [26, 28], "backtrac": [26, 28], "examin": [26, 28], "expr": [26, 31], "whati": [26, 31], "alter": [26, 28], "topic": 26, "complex": [26, 43], "test_info": [27, 30], "test_info_arg": 27, "25": [27, 30, 31], "test_info_loc": 27, "sum_local_var": [27, 30], "uniniti": 27, "000": [27, 30], "repeat": [27, 30, 46], "__ocl_dbg_gid0": [27, 30], "__ocl_dbg_gid1": [27, 30], "__ocl_dbg_gid2": [27, 30], "__ocl_dbg_lid0": [27, 30], "__ocl_dbg_lid1": [27, 30], "__ocl_dbg_lid2": [27, 30], "__ocl_dbg_grid0": [27, 30], "__ocl_dbg_grid1": [27, 30], "__ocl_dbg_grid2": [27, 30], "24": [27, 30], "16": [27, 30], "004": [27, 30], "240": [27, 30], "016xuu": [27, 30], "256wuu": [27, 30], "42949672970": [27, 30], "93825037590528": [27, 30], "4612811918334230528": [27, 30], "unset": 28, "significantli": 28, "consumpt": 28, "larg": 28, "Not": 28, "yet": [28, 42, 45], "relev": 28, "graphic": 28, "bind": 28, "nopython": 28, "stabl": 28, "twice": [28, 33], "influenc": 30, "effect": 30, "26": 30, "9795852899551392": 30, "22986688613891601": 30, "tmp": [30, 35, 46], "kernel_11059955544143858990_e6df1": 30, "dbgelf": 30, "analys": 30, "block": [30, 44], "del": 30, "annot": 30, "21": [30, 32], "1d": [30, 34], "2load_glob": 30, "__init__": 30, "4load_method": 30, "getattr": 30, "attr": 30, "0x7f82b8bae430": 30, "const6": 30, "kw": 30, "vararg": 30, "none": [30, 37, 43], "uint32": 30, "int64": [30, 34, 37], "16binary_subscr": 30, "getitem": 30, "fn": 30, "const18": 30, "float64": [30, 37], "28binary_subscr": 30, "11": 30, "const30": 30, "12": 30, "40binary_add": 30, "const48": 30, "19": [30, 32], "nonetyp": 30, "50return_valu": 30, "last": 30, "shown": 30, "workaround": 30, "expand": 30, "reviv": 30, "until": [30, 44], "sum_local_vars_rev": 30, "0x7fcdf7e8c4c0": 30, "27": 30, "30": [30, 32], "48load_glob": 30, "dpexfunctiontempl": 30, "0x7fce12e5cc40": 30, "52call_funct": 30, "const56": 30, "58return_valu": 30, "93825034429928": 30, "93825034429936": 30, "4599075939470750515": 30, "test_breakpoint": 31, "test_breakpoint_with_condition_by_function_argu": 31, "than": 31, "posibl": 31, "samp": 31, "togeth": 31, "numba_dump_annot": 31, "gpgpu": 32, "video": 32, "18": 32, "fedora": 32, "sle": 32, "sp1": 32, "render": 32, "cento": 32, "31": 32, "administr": 32, "sudo": 32, "root": 32, "privileg": 32, "owner": 32, "renderd": 32, "card": 32, "usermod": 32, "usernam": 32, "19533": 32, "download": 32, "dpkg": 32, "deb": 32, "ld_library_path": 32, "my": 32, "my_active_neo": 32, "client": 32, "icd": 32, "ocl_icd_filenam": 32, "overwrit": 32, "ocl_icd_vendor": 32, "libigdrcl": 32, "libintelocl": 32, "r": [32, 42, 46], "tm": 32, "loader": 32, "modinfo": 32, "remov": 32, "o": [32, 35], "signatur": 32, "below": [33, 40, 46], "forward": 33, "pc": 33, "0x00000000fffeb630": 33, "dpex_func": 33, "regexp": 34, "produc": 34, "lot": 34, "typic": 34, "veri": 34, "long": 34, "regular": [34, 45], "mutabl": 34, "align": 34, "struct": 34, "addrspac": 34, "i64": 34, "drop": 35, "univers": [35, 36, 39], "foo": 35, "sqrt": [35, 43, 46], "naiv": 35, "pairwis": [35, 46], "distanc": [35, 46], "x1": 35, "x2": 35, "d": [35, 46], "na\u00efv": 35, "impl": 35, "euclidean": [35, 46], "x1_row": 35, "x2_row": 35, "x1_col": 35, "float0": 35, "outermost": 35, "j": [35, 46], "exclidean": 35, "k": [35, 46], "qualifi": [36, 39], "ari": 37, "int32": [37, 42], "increment": 37, "Its": 37, "decrement": 37, "atomic_reduct": 37, "notion": 38, "a_device_funct": 38, "another_device_funct": 38, "a_kernel_funct": 38, "normal": [38, 41], "capabl": 38, "concept": 39, "being": 39, "offer": 39, "piec": 39, "bigger": 39, "chunk": 39, "48": 39, "bear": 39, "roc": 39, "proprietari": 39, "declar": 39, "invoc": 39, "disjoint": 40, "pool": 40, "among": 40, "spdx": 40, "filecopyrighttext": 40, "2024": 40, "corpor": 40, "kernel_vector_sum": [40, 46], "a_np": [40, 46], "b_np": [40, 46], "c_np": [40, 46], "assert_equ": [40, 46], "__name__": 40, "static": 40, "private_memori": 40, "intrins": 40, "private_memory_kernel": 40, "preload": 40, "hold": 40, "determinist": 40, "select_default_devic": 40, "arr": 40, "orig": 40, "astyp": 40, "print_device_info": 40, "arr_out": 40, "assert_allclos": 40, "ranf": 41, "random_sampl": 41, "rand": 41, "randint": 41, "random_integ": 41, "beta": 41, "binomi": 41, "chisquar": 41, "exponenti": 41, "gamma": [41, 43], "geometr": 41, "gumbel": 41, "hypergeometr": 41, "laplac": 41, "lognorm": 41, "multinomi": 41, "multivariate_norm": 41, "negative_binomi": 41, "poisson": 41, "rayleigh": 41, "standard_cauchi": 41, "standard_exponenti": 41, "standard_gamma": 41, "standard_norm": 41, "uniform": 41, "weibul": 41, "numba_dpex_debug": 41, "look": 41, "stdout": 41, "approach": 42, "summat": [42, 46], "sum_reduct": 42, "reduc": 42, "sum_reduction_kernel": 42, "nex": 42, "iter": 42, "sum_reduc": 42, "len": [42, 43], "half": 42, "math": [42, 43], "floor": [42, 43], "sum_reduction_recursive_ocl": 42, "input_s": 42, "partial_sum": 42, "local_id": 42, "global_id": 42, "group_siz": 42, "get_local_s": [42, 46], "group_id": 42, "local_sum": 42, "64": 42, "divid": 42, "workgroup": 42, "2x2": 42, "sum_recursive_reduct": 42, "dinp": 42, "dpartial_sum": 42, "nb_work_group": 42, "passed_s": 42, "els": 42, "gr": 42, "lr": 42, "work_group_s": 42, "sum_reduction_ocl": 42, "bool": 43, "ab": 43, "round": 43, "aco": 43, "asin": 43, "atan": 43, "acosh": 43, "asinh": 43, "atanh": 43, "co": 43, "sin": 43, "tan": 43, "cosh": 43, "sinh": 43, "tanh": 43, "erf": 43, "erfc": 43, "exp": 43, "expm1": 43, "fab": 43, "lgamma": 43, "log": 43, "log10": 43, "log1p": 43, "ceil": 43, "eq": 43, "floordiv": 43, "ge": 43, "iadd": 43, "ifloordiv": 43, "imod": 43, "imul": 43, "ipow": 43, "isub": 43, "itruediv": 43, "le": 43, "lshift": 43, "lt": 43, "mod": 43, "ne": 43, "neg": 43, "not_": 43, "or_": 43, "po": 43, "pow": 43, "truediv": 43, "final": 43, "comprehens": 43, "dict": 43, "yield": 43, "whole": 43, "tradit": 44, "caller": 44, "read": 44, "flush": 44, "syncthread": 44, "routin": 45, "although": 45, "fulli": 45, "guvector": 45, "cannot": [45, 46], "ongo": 45, "progress": 45, "blacksholes_njit": 45, "eschew": 45, "fpga": 46, "characterist": 46, "scalar": 46, "pair": 46, "wise": 46, "xshape0": 46, "xshape1": 46, "d0": 46, "total_tim": 46, "get_global_s": 46, "get_num_group": 46}, "objects": {"": [[13, 0, 0, "-", "numba_dpex"]], "numba_dpex": [[4, 0, 0, "-", "kernel_api"]], "numba_dpex.kernel_api": [[4, 1, 1, "", "AddressSpace"], [4, 1, 1, "", "AtomicRef"], [4, 1, 1, "", "Group"], [4, 1, 1, "", "Item"], [4, 1, 1, "", "MemoryOrder"], [4, 1, 1, "", "MemoryScope"], [4, 1, 1, "", "NdItem"], [4, 1, 1, "", "NdRange"], [4, 1, 1, "", "Range"], [1, 0, 0, "-", "atomic_ref"], [2, 0, 0, "-", "barrier"], [4, 4, 1, "", "call_kernel"], [3, 0, 0, "-", "flag_enum"], [4, 4, 1, "", "group_barrier"], [5, 0, 0, "-", "index_space_ids"], [6, 0, 0, "-", "launcher"], [7, 0, 0, "-", "memory_enums"], [8, 0, 0, "-", "ranges"]], "numba_dpex.kernel_api.AddressSpace": [[4, 2, 1, "", "CONSTANT"], [4, 2, 1, "", "GENERIC"], [4, 2, 1, "", "GLOBAL"], [4, 2, 1, "", "LOCAL"], [4, 2, 1, "", "PRIVATE"]], "numba_dpex.kernel_api.AtomicRef": [[4, 3, 1, "", "compare_exchange"], [4, 3, 1, "", "exchange"], [4, 3, 1, "", "fetch_add"], [4, 3, 1, "", "fetch_and"], [4, 3, 1, "", "fetch_max"], [4, 3, 1, "", "fetch_min"], [4, 3, 1, "", "fetch_or"], [4, 3, 1, "", "fetch_sub"], [4, 3, 1, "", "fetch_xor"], [4, 3, 1, "", "load"], [4, 3, 1, "", "store"]], "numba_dpex.kernel_api.Group": [[4, 3, 1, "", "get_group_id"], [4, 3, 1, "", "get_group_linear_id"], [4, 3, 1, "", "get_group_linear_range"], [4, 3, 1, "", "get_group_range"], [4, 3, 1, "", "get_local_linear_range"], [4, 3, 1, "", "get_local_range"]], "numba_dpex.kernel_api.Item": [[4, 3, 1, "", "get_id"], [4, 3, 1, "", "get_linear_id"], [4, 3, 1, "", "get_range"]], "numba_dpex.kernel_api.MemoryOrder": [[4, 2, 1, "", "ACQUIRE"], [4, 2, 1, "", "ACQ_REL"], [4, 2, 1, "", "CONSUME_UNSUPPORTED"], [4, 2, 1, "", "RELAXED"], [4, 2, 1, "", "RELEASE"], [4, 2, 1, "", "SEQ_CST"]], "numba_dpex.kernel_api.MemoryScope": [[4, 2, 1, "", "DEVICE"], [4, 2, 1, "", "SUB_GROUP"], [4, 2, 1, "", "SYSTEM"], [4, 2, 1, "", "WORK_GROUP"], [4, 2, 1, "", "WORK_ITEM"]], "numba_dpex.kernel_api.NdItem": [[4, 3, 1, "", "get_global_id"], [4, 3, 1, "", "get_global_linear_id"], [4, 3, 1, "", "get_global_range"], [4, 3, 1, "", "get_group"], [4, 3, 1, "", "get_local_id"], [4, 3, 1, "", "get_local_linear_id"], [4, 3, 1, "", "get_local_range"]], "numba_dpex.kernel_api.NdRange": [[4, 3, 1, "", "get_global_range"], [4, 3, 1, "", "get_local_range"]], "numba_dpex.kernel_api.Range": [[4, 2, 1, "", "UNDEFINED_DIMENSION"], [4, 3, 1, "", "get"], [4, 3, 1, "", "size"]], "numba_dpex.kernel_api.atomic_ref": [[1, 1, 1, "", "AtomicRef"]], "numba_dpex.kernel_api.atomic_ref.AtomicRef": [[1, 3, 1, "", "compare_exchange"], [1, 3, 1, "", "exchange"], [1, 3, 1, "", "fetch_add"], [1, 3, 1, "", "fetch_and"], [1, 3, 1, "", "fetch_max"], [1, 3, 1, "", "fetch_min"], [1, 3, 1, "", "fetch_or"], [1, 3, 1, "", "fetch_sub"], [1, 3, 1, "", "fetch_xor"], [1, 3, 1, "", "load"], [1, 3, 1, "", "store"]], "numba_dpex.kernel_api.barrier": [[2, 4, 1, "", "group_barrier"]], "numba_dpex.kernel_api.flag_enum": [[3, 1, 1, "", "FlagEnum"]], "numba_dpex.kernel_api.flag_enum.FlagEnum": [[3, 3, 1, "", "basetype"]], "numba_dpex.kernel_api.index_space_ids": [[5, 1, 1, "", "Group"], [5, 1, 1, "", "Item"], [5, 1, 1, "", "NdItem"]], "numba_dpex.kernel_api.index_space_ids.Group": [[5, 3, 1, "", "get_group_id"], [5, 3, 1, "", "get_group_linear_id"], [5, 3, 1, "", "get_group_linear_range"], [5, 3, 1, "", "get_group_range"], [5, 3, 1, "", "get_local_linear_range"], [5, 3, 1, "", "get_local_range"]], "numba_dpex.kernel_api.index_space_ids.Item": [[5, 3, 1, "", "get_id"], [5, 3, 1, "", "get_linear_id"], [5, 3, 1, "", "get_range"]], "numba_dpex.kernel_api.index_space_ids.NdItem": [[5, 3, 1, "", "get_global_id"], [5, 3, 1, "", "get_global_linear_id"], [5, 3, 1, "", "get_global_range"], [5, 3, 1, "", "get_group"], [5, 3, 1, "", "get_local_id"], [5, 3, 1, "", "get_local_linear_id"], [5, 3, 1, "", "get_local_range"]], "numba_dpex.kernel_api.launcher": [[6, 4, 1, "", "call_kernel"]], "numba_dpex.kernel_api.memory_enums": [[7, 1, 1, "", "AddressSpace"], [7, 1, 1, "", "MemoryOrder"], [7, 1, 1, "", "MemoryScope"]], "numba_dpex.kernel_api.memory_enums.AddressSpace": [[7, 2, 1, "", "CONSTANT"], [7, 2, 1, "", "GENERIC"], [7, 2, 1, "", "GLOBAL"], [7, 2, 1, "", "LOCAL"], [7, 2, 1, "", "PRIVATE"]], "numba_dpex.kernel_api.memory_enums.MemoryOrder": [[7, 2, 1, "", "ACQUIRE"], [7, 2, 1, "", "ACQ_REL"], [7, 2, 1, "", "CONSUME_UNSUPPORTED"], [7, 2, 1, "", "RELAXED"], [7, 2, 1, "", "RELEASE"], [7, 2, 1, "", "SEQ_CST"]], "numba_dpex.kernel_api.memory_enums.MemoryScope": [[7, 2, 1, "", "DEVICE"], [7, 2, 1, "", "SUB_GROUP"], [7, 2, 1, "", "SYSTEM"], [7, 2, 1, "", "WORK_GROUP"], [7, 2, 1, "", "WORK_ITEM"]], "numba_dpex.kernel_api.ranges": [[8, 1, 1, "", "NdRange"], [8, 1, 1, "", "Range"]], "numba_dpex.kernel_api.ranges.NdRange": [[8, 3, 1, "", "get_global_range"], [8, 3, 1, "", "get_local_range"]], "numba_dpex.kernel_api.ranges.Range": [[8, 2, 1, "", "UNDEFINED_DIMENSION"], [8, 3, 1, "", "get"], [8, 3, 1, "", "size"]]}, "objtypes": {"0": "py:module", "1": "py:class", "2": "py:attribute", "3": "py:method", "4": "py:function"}, "objnames": {"0": ["py", "module", "Python module"], "1": ["py", "class", "Python class"], "2": ["py", "attribute", "Python attribute"], "3": ["py", "method", "Python method"], "4": ["py", "function", "Python function"]}, "titleterms": {"api": 0, "refer": 0, "numba_dpex": [1, 2, 3, 4, 5, 6, 7, 8, 43, 45], "kernel_api": [1, 2, 3, 4, 5, 6, 7, 8], "atomic_ref": 1, "overview": [1, 2, 3, 4, 5, 6, 7, 8, 15], "class": [1, 3, 4, 5, 7, 8], "method": [1, 3, 4, 5, 8], "barrier": 2, "function": [2, 4, 6, 22, 31, 34, 38, 41, 43, 44, 45, 46], "flag_enum": 3, "submodul": 4, "attribut": [4, 7, 8], "index_space_id": 5, "launcher": 6, "memory_enum": 7, "rang": [8, 35], "contribut": 9, "guid": 9, "classif": 9, "develop": [9, 13], "cycl": 9, "issu": [9, 23], "pull": 9, "request": 9, "code": [9, 29], "guidelin": 9, "unit": 9, "test": [9, 11], "document": [9, 18, 39], "tip": [9, 23], "list": 10, "exampl": [10, 11, 20, 24, 27, 28, 30, 31, 34, 37, 42, 45], "todo": [10, 38], "benchmark": 10, "jupyt": 10, "notebook": 10, "get": 11, "start": 11, "instal": 11, "pre": 11, "built": [11, 43], "conda": 11, "packag": 11, "build": 11, "from": 11, "sourc": 11, "insid": [11, 43, 45], "docker": 11, "us": [11, 18, 29, 30], "imag": 11, "glossari": 12, "data": [13, 16, 24, 31, 34, 46], "parallel": [13, 35, 46], "extens": 13, "numba": [13, 17, 19, 29, 30, 31, 45], "misc": 13, "note": [13, 17], "licens": 14, "main": 15, "featur": [15, 26, 28, 31, 43], "portabl": 15, "kernel": [15, 39, 43, 45, 46], "program": [15, 16, 39], "dpjit": 15, "decor": 15, "model": 16, "recogn": 16, "avail": 16, "devic": [16, 38, 42], "specifi": 16, "offload": [16, 35], "target": 16, "share": 16, "comput": 16, "follow": [16, 39], "releas": 17, "changelog": 17, "0": [17, 31], "21": 17, "4": 17, "2023": 17, "10": 17, "12": 17, "fix": 17, "3": [17, 30], "09": 17, "28": 17, "ad": [17, 31], "chang": 17, "remov": 17, "2": [17, 30, 42, 45], "08": 17, "07": 17, "1": [17, 30, 42, 45], "17": 17, "06": 17, "20": 17, "04": 17, "03": 17, "deprec": 17, "19": 17, "2022": 17, "11": 17, "18": 17, "02": 17, "22": 17, "2021": 17, "30": 17, "15": 17, "16": 17, "25": 17, "14": 17, "05": 17, "27": 17, "26": 17, "13": 17, "2020": 17, "version": 17, "48": 17, "dppy": 17, "june": 17, "29": 17, "link": 18, "companion": [18, 32], "configur": [19, 25], "option": 19, "dpex": 19, "alter": [20, 29], "execut": 20, "assign": 20, "variabl": [20, 30], "backtrac": 21, "breakpoint": [22, 23, 31], "break": 22, "filenam": 22, "linenumb": 22, "cond": 22, "nest": 22, "common": 23, "ar": 23, "hit": 23, "debug": [23, 25, 28, 30, 31, 32], "i": 23, "stabl": 23, "twice": 23, "examin": [24, 34], "print": 24, "expr": 24, "complex": [24, 31, 34], "type": [24, 31, 34, 43], "environ": 25, "support": [26, 37, 40, 41, 42, 43], "inform": 27, "about": 27, "frame": 27, "info": [27, 30, 31, 34], "arg": [27, 31, 34], "local": [27, 30, 31], "intel": 28, "distribut": [28, 41], "gdb": [28, 29], "requir": 28, "usag": [28, 45], "limit": [28, 29], "argument": [29, 31], "modifi": 29, "": 29, "direct": 29, "bind": 29, "nopython": 29, "mode": 29, "optim": 30, "level": 30, "llvm": 30, "lifetim": 30, "ir": 30, "numba_extend_variable_lifetim": [30, 31], "numba_dump_annot": 30, "55": 31, "extend": 31, "condit": 31, "displai": 31, "set": [32, 33], "up": 32, "machin": 32, "graphic": 32, "driver": 32, "neo": 32, "dcd": 32, "step": 33, "stepi": 33, "next": 33, "schedul": 33, "lock": 33, "symbol": 34, "tabl": 34, "whati": 34, "ptype": 34, "compil": 35, "dpnp": 35, "statement": 35, "tutori": 36, "atom": 37, "oper": 37, "full": [37, 42, 45], "write": [38, 46], "basic": [39, 45], "thi": 39, "cover": 39, "chapter": 39, "address": 40, "space": 40, "qualifi": 40, "random": 41, "number": 41, "gener": 41, "simpl": 41, "reduct": 42, "sycl": 42, "python": 43, "standard": 43, "librari": 43, "modul": 43, "unsupport": 43, "construct": 43, "numpi": 43, "synchron": 44, "univers": 45, "call": 45, "vector": 45, "declar": 46, "invoc": 46, "index": 46}, "envversion": {"sphinx.domains.c": 3, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 9, "sphinx.domains.index": 1, "sphinx.domains.javascript": 3, "sphinx.domains.math": 2, "sphinx.domains.python": 4, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "sphinx.ext.todo": 2, "sphinx.ext.intersphinx": 1, "sphinx": 60}, "alltitles": {"API Reference": [[0, "api-reference"]], "numba_dpex.kernel_api.atomic_ref": [[1, "module-numba_dpex.kernel_api.atomic_ref"]], "Overview": [[1, "overview"], [2, "overview"], [3, "overview"], [4, "overview"], [5, "overview"], [6, "overview"], [7, "overview"], [8, "overview"], [15, "id2"]], "Classes": [[1, "id1"], [1, "classes"], [3, "id1"], [3, "classes"], [4, "id1"], [4, "classes"], [5, "id3"], [5, "classes"], [7, "id1"], [7, "classes"], [8, "id1"], [8, "classes"]], "Methods": [[1, "id2"], [3, "id2"], [4, "id3"], [4, "id4"], [4, "id5"], [4, "id6"], [4, "id10"], [4, "id12"], [5, "id4"], [5, "id5"], [5, "id6"], [8, "id3"], [8, "id4"]], "numba_dpex.kernel_api.barrier": [[2, "module-numba_dpex.kernel_api.barrier"]], "Function": [[2, "id1"], [4, "id2"], [6, "id1"]], "Functions": [[2, "functions"], [4, "functions"], [6, "functions"]], "numba_dpex.kernel_api.flag_enum": [[3, "module-numba_dpex.kernel_api.flag_enum"]], "numba_dpex.kernel_api": [[4, "module-numba_dpex.kernel_api"]], "Submodules": [[4, "submodules"]], "Attributes": [[4, "id7"], [4, "id8"], [4, "id9"], [4, "id11"], [7, "id2"], [7, "id3"], [7, "id4"], [8, "id2"]], "numba_dpex.kernel_api.index_space_ids": [[5, "module-numba_dpex.kernel_api.index_space_ids"]], "numba_dpex.kernel_api.launcher": [[6, "module-numba_dpex.kernel_api.launcher"]], "numba_dpex.kernel_api.memory_enums": [[7, "module-numba_dpex.kernel_api.memory_enums"]], "numba_dpex.kernel_api.ranges": [[8, "module-numba_dpex.kernel_api.ranges"]], "Contribution Guide": [[9, "contribution-guide"]], "Classification of Contributions": [[9, "classification-of-contributions"]], "Development Cycle": [[9, "development-cycle"]], "Issues and Pull Requests": [[9, "issues-and-pull-requests"]], "Coding Guidelines": [[9, "coding-guidelines"]], "Unit Testing": [[9, "unit-testing"]], "Documentation": [[9, "documentation"]], "Tips for Developers": [[9, "tips-for-developers"]], "List of examples": [[10, "list-of-examples"]], "Todo": [[10, "id2"], [10, "id3"], [10, "id4"], [38, "id1"]], "Benchmarks": [[10, "benchmarks"]], "Jupyter* Notebooks": [[10, "jupyter-notebooks"]], "Getting Started": [[11, "id2"]], "Installing pre-built conda packages": [[11, "installing-pre-built-conda-packages"]], "Building from source": [[11, "building-from-source"]], "Building inside Docker": [[11, "building-inside-docker"]], "Building": [[11, "building"]], "Using the pre-built images": [[11, "using-the-pre-built-images"]], "Testing": [[11, "testing"]], "Examples": [[11, "examples"]], "Glossary": [[12, "id2"]], "Data Parallel Extension for Numba*": [[13, "id2"]], "Development": [[13, null]], "Misc Notes": [[13, null]], "License": [[14, "id2"]], "Main Features": [[15, "main-features"]], "Portable Kernel Programming": [[15, "portable-kernel-programming"]], "dpjit decorator": [[15, "dpjit-decorator"]], "Programming Model": [[16, "id2"]], "Recognizing available devices": [[16, "recognizing-available-devices"]], "Specifying offload target": [[16, "specifying-offload-target"]], "Data sharing": [[16, "data-sharing"]], "Compute follows data": [[16, "compute-follows-data"]], "Release Notes": [[17, "id2"]], "Changelog": [[17, "changelog"]], "[0.21.4] - 2023-10-12": [[17, "id1"]], "Fixed": [[17, "fixed"], [17, "id3"], [17, "id5"], [17, "id10"], [17, "id14"], [17, "id18"], [17, "id22"], [17, "id26"], [17, "id33"], [17, "id38"], [17, "id45"], [17, "id51"], [17, "id56"], [17, "id58"], [17, "id61"], [17, "id65"], [17, "id67"], [17, "id71"]], "[0.21.3] - 2023-09-28": [[17, "id2"]], "Added": [[17, "added"], [17, "id12"], [17, "id17"], [17, "id20"], [17, "id25"], [17, "id28"], [17, "id31"], [17, "id44"], [17, "id49"], [17, "id53"], [17, "id59"], [17, "id63"], [17, "id69"], [17, "id73"]], "Changed": [[17, "changed"], [17, "id6"], [17, "id9"], [17, "id13"], [17, "id21"], [17, "id29"], [17, "id32"], [17, "id35"], [17, "id37"], [17, "id40"], [17, "id42"], [17, "id47"], [17, "id50"], [17, "id54"], [17, "id64"], [17, "id70"], [17, "id74"]], "Removed": [[17, "removed"], [17, "id7"], [17, "id15"], [17, "id23"], [17, "id55"], [17, "id75"]], "[0.21.2] - 2023-08-07": [[17, "id4"]], "[0.21.1] - 2023-07-17": [[17, "id8"]], "[0.21.0] - 2023-06-17": [[17, "id11"]], "[0.20.1] - 2023-04-07": [[17, "id16"]], "[0.20.0] - 2023-03-06": [[17, "id19"]], "Deprecated": [[17, "deprecated"]], "[0.19.0] - 2022-11-21": [[17, "id24"]], "[0.18.1] - 2022-08-06": [[17, "id27"]], "[0.18.0] - 2022-02-22": [[17, "id30"]], "[0.17.4] - 2021-12-02": [[17, "id34"]], "[0.17.3] - 2021-11-30": [[17, "id36"]], "[0.17.2] - 2021-11-15": [[17, "id39"]], "[0.17.1] - 2021-11-10": [[17, "id41"]], "[0.17.0] - 2021-11-03": [[17, "id43"]], "[0.16.1] - 2021-10-20": [[17, "id46"]], "[0.16.0] - 2021-09-28": [[17, "id48"]], "[0.15.0] - 2021-08-25": [[17, "id52"]], "[0.14.4] - 2021-07-09": [[17, "id57"]], "[0.14.3] - 2021-05-27": [[17, "id60"]], "[0.14.2] - 2021-05-26": [[17, "id62"]], "[0.13.1] - 2021-03-11": [[17, "id66"]], "[0.13.0] - 2021-03-02": [[17, "id68"]], "[0.12.0] - 2020-12-17": [[17, "id72"]], "NUMBA Version 0.48.0 + DPPY Version 0.3.0 (June 29, 2020)": [[17, "numba-version-0-48-0-dppy-version-0-3-0-june-29-2020"]], "Useful links": [[18, "id2"]], "Companion documentation": [[18, "id3"]], "Configuration Options for numba-dpex": [[19, "configuration-options-for-numba-dpex"]], "Altering Execution": [[20, "altering-execution"]], "Assignment to Variables": [[20, "assignment-to-variables"]], "Example": [[20, "example"], [27, "example"], [27, "id4"], [30, "example"], [31, "example"], [34, "example"], [37, "example"]], "Backtrace": [[21, "backtrace"]], "Breakpoints": [[22, "breakpoints"]], "break function": [[22, "break-function"]], "break filename:linenumber": [[22, "break-filename-linenumber"]], "break filename:function": [[22, "break-filename-function"]], "break \u2026 if cond": [[22, "break-if-cond"]], "Breakpoints with nested functions": [[22, "breakpoints-with-nested-functions"]], "Common issues and tips": [[23, "common-issues-and-tips"]], "Breakpoints are not hit": [[23, "breakpoints-are-not-hit"]], "Debugging is not stable": [[23, "debugging-is-not-stable"]], "Breakpoint is hit twice": [[23, "breakpoint-is-hit-twice"]], "Examining Data": [[24, "examining-data"]], "print expr": [[24, "print-expr"]], "Example - Complex Data Types": [[24, "example-complex-data-types"], [34, "example-complex-data-types"]], "Configure debugging environment": [[25, "configure-debugging-environment"]], "Supported Features": [[26, "supported-features"]], "Information About a Frame": [[27, "information-about-a-frame"]], "info args": [[27, "info-args"]], "info locals": [[27, "info-locals"]], "Debugging with Intel\u00ae Distribution for GDB*": [[28, "debugging-with-intel-distribution-for-gdb"]], "Requirements": [[28, "requirements"]], "Example of Intel\u00ae Distribution for GDB* usage": [[28, "example-of-intel-distribution-for-gdb-usage"]], "Features and Limitations": [[28, "features-and-limitations"]], "Limitations": [[29, "limitations"]], "Altering arguments modified in code": [[29, "altering-arguments-modified-in-code"]], "Using Numba\u2019s direct gdb bindings in nopython mode": [[29, "using-numba-s-direct-gdb-bindings-in-nopython-mode"]], "Debugging Local Variables": [[30, "debugging-local-variables"]], "Optimization Level for LLVM": [[30, "optimization-level-for-llvm"]], "Local Variables Lifetime in Numba IR": [[30, "local-variables-lifetime-in-numba-ir"]], "Example 1 - Using NUMBA_EXTEND_VARIABLE_LIFETIMES": [[30, "example-1-using-numba-extend-variable-lifetimes"]], "Example 2 - Using NUMBA_DUMP_ANNOTATION": [[30, "example-2-using-numba-dump-annotation"]], "Example 3 - Using info locals": [[30, "example-3-using-info-locals"]], "Debugging Features in Numba 0.55": [[31, "debugging-features-in-numba-0-55"]], "Added info args": [[31, "added-info-args"]], "Extended info locals": [[31, "extended-info-locals"]], "Breakpoint with condition by function argument": [[31, "breakpoint-with-condition-by-function-argument"]], "Added NUMBA_EXTEND_VARIABLE_LIFETIMES": [[31, "added-numba-extend-variable-lifetimes"]], "Displaying Complex Data Types": [[31, "displaying-complex-data-types"]], "Set up the machine for debugging": [[32, "set-up-the-machine-for-debugging"]], "Graphics driver": [[32, "graphics-driver"]], "NEO driver": [[32, "neo-driver"]], "Debug companion driver (DCD)": [[32, "debug-companion-driver-dcd"]], "Stepping": [[33, "stepping"]], "step": [[33, "step"]], "stepi": [[33, "stepi"]], "next": [[33, "next"]], "set scheduler-locking step": [[33, "set-scheduler-locking-step"]], "Examining the Symbol Table": [[34, "examining-the-symbol-table"]], "info functions": [[34, "info-functions"]], "whatis [arg] and ptype [arg]": [[34, "whatis-arg-and-ptype-arg"]], "Compiling and Offloading dpnp statements": [[35, "compiling-and-offloading-dpnp-statements"]], "Parallel Range": [[35, "parallel-range"]], "Tutorials": [[36, "tutorials"]], "Supported Atomic Operations": [[37, "supported-atomic-operations"]], "Full examples": [[37, "full-examples"], [42, "full-examples"]], "Writing Device Functions": [[38, "writing-device-functions"]], "Kernel Programming Basics": [[39, "kernel-programming-basics"]], "This document will cover the following chapters:": [[39, null]], "Supported Address Space Qualifiers": [[40, "supported-address-space-qualifiers"]], "Random Number Generation": [[41, "random-number-generation"]], "Supported functions": [[41, "supported-functions"]], "Simple random": [[41, "simple-random"]], "Distribution": [[41, "distribution"]], "Reduction on SYCL-supported Devices": [[42, "reduction-on-sycl-supported-devices"]], "Example 1": [[42, "example-1"]], "Example 2": [[42, "example-2"]], "Supported Python Features inside numba_dpex.kernel": [[43, "supported-python-features-inside-numba-dpex-kernel"]], "Built-in types": [[43, "built-in-types"]], "Built-in functions": [[43, "built-in-functions"]], "Standard library modules": [[43, "standard-library-modules"]], "Unsupported Constructs": [[43, "unsupported-constructs"]], "NumPy support": [[43, "numpy-support"]], "Synchronization Functions": [[44, "synchronization-functions"]], "Universal Functions": [[45, "universal-functions"]], "Example 1: Basic Usage": [[45, "example-1-basic-usage"]], "Example 2: Calling numba.vectorize inside a numba_dpex.kernel": [[45, "example-2-calling-numba-vectorize-inside-a-numba-dpex-kernel"]], "Full Examples": [[45, "full-examples"]], "Writing Data Parallel Kernels": [[46, "writing-data-parallel-kernels"]], "Kernel Declaration": [[46, "kernel-declaration"]], "Kernel Invocation": [[46, "kernel-invocation"]], "Kernel Indexing Functions": [[46, "kernel-indexing-functions"]]}, "indexentries": {"atomicref (class in numba_dpex.kernel_api.atomic_ref)": [[1, "numba_dpex.kernel_api.atomic_ref.AtomicRef"]], "compare_exchange() (atomicref method)": [[1, "numba_dpex.kernel_api.atomic_ref.AtomicRef.compare_exchange"], [4, "numba_dpex.kernel_api.AtomicRef.compare_exchange"]], "exchange() (atomicref method)": [[1, "numba_dpex.kernel_api.atomic_ref.AtomicRef.exchange"], [4, "numba_dpex.kernel_api.AtomicRef.exchange"]], "fetch_add() (atomicref method)": [[1, "numba_dpex.kernel_api.atomic_ref.AtomicRef.fetch_add"], [4, "numba_dpex.kernel_api.AtomicRef.fetch_add"]], "fetch_and() (atomicref method)": [[1, "numba_dpex.kernel_api.atomic_ref.AtomicRef.fetch_and"], [4, "numba_dpex.kernel_api.AtomicRef.fetch_and"]], "fetch_max() (atomicref method)": [[1, "numba_dpex.kernel_api.atomic_ref.AtomicRef.fetch_max"], [4, "numba_dpex.kernel_api.AtomicRef.fetch_max"]], "fetch_min() (atomicref method)": [[1, "numba_dpex.kernel_api.atomic_ref.AtomicRef.fetch_min"], [4, "numba_dpex.kernel_api.AtomicRef.fetch_min"]], "fetch_or() (atomicref method)": [[1, "numba_dpex.kernel_api.atomic_ref.AtomicRef.fetch_or"], [4, "numba_dpex.kernel_api.AtomicRef.fetch_or"]], "fetch_sub() (atomicref method)": [[1, "numba_dpex.kernel_api.atomic_ref.AtomicRef.fetch_sub"], [4, "numba_dpex.kernel_api.AtomicRef.fetch_sub"]], "fetch_xor() (atomicref method)": [[1, "numba_dpex.kernel_api.atomic_ref.AtomicRef.fetch_xor"], [4, "numba_dpex.kernel_api.AtomicRef.fetch_xor"]], "load() (atomicref method)": [[1, "numba_dpex.kernel_api.atomic_ref.AtomicRef.load"], [4, "numba_dpex.kernel_api.AtomicRef.load"]], "module": [[1, "module-numba_dpex.kernel_api.atomic_ref"], [2, "module-numba_dpex.kernel_api.barrier"], [3, "module-numba_dpex.kernel_api.flag_enum"], [4, "module-numba_dpex.kernel_api"], [5, "module-numba_dpex.kernel_api.index_space_ids"], [6, "module-numba_dpex.kernel_api.launcher"], [7, "module-numba_dpex.kernel_api.memory_enums"], [8, "module-numba_dpex.kernel_api.ranges"], [13, "module-numba_dpex"]], "numba_dpex.kernel_api.atomic_ref": [[1, "module-numba_dpex.kernel_api.atomic_ref"]], "store() (atomicref method)": [[1, "numba_dpex.kernel_api.atomic_ref.AtomicRef.store"], [4, "numba_dpex.kernel_api.AtomicRef.store"]], "group_barrier() (in module numba_dpex.kernel_api.barrier)": [[2, "numba_dpex.kernel_api.barrier.group_barrier"]], "numba_dpex.kernel_api.barrier": [[2, "module-numba_dpex.kernel_api.barrier"]], "flagenum (class in numba_dpex.kernel_api.flag_enum)": [[3, "numba_dpex.kernel_api.flag_enum.FlagEnum"]], "basetype() (flagenum class method)": [[3, "numba_dpex.kernel_api.flag_enum.FlagEnum.basetype"]], "numba_dpex.kernel_api.flag_enum": [[3, "module-numba_dpex.kernel_api.flag_enum"]], "acquire (memoryorder attribute)": [[4, "numba_dpex.kernel_api.MemoryOrder.ACQUIRE"], [7, "numba_dpex.kernel_api.memory_enums.MemoryOrder.ACQUIRE"]], "acq_rel (memoryorder attribute)": [[4, "numba_dpex.kernel_api.MemoryOrder.ACQ_REL"], [7, "numba_dpex.kernel_api.memory_enums.MemoryOrder.ACQ_REL"]], "addressspace (class in numba_dpex.kernel_api)": [[4, "numba_dpex.kernel_api.AddressSpace"]], "atomicref (class in numba_dpex.kernel_api)": [[4, "numba_dpex.kernel_api.AtomicRef"]], "constant (addressspace attribute)": [[4, "numba_dpex.kernel_api.AddressSpace.CONSTANT"], [7, "numba_dpex.kernel_api.memory_enums.AddressSpace.CONSTANT"]], "consume_unsupported (memoryorder attribute)": [[4, "numba_dpex.kernel_api.MemoryOrder.CONSUME_UNSUPPORTED"], [7, "numba_dpex.kernel_api.memory_enums.MemoryOrder.CONSUME_UNSUPPORTED"]], "device (memoryscope attribute)": [[4, "numba_dpex.kernel_api.MemoryScope.DEVICE"], [7, "numba_dpex.kernel_api.memory_enums.MemoryScope.DEVICE"]], "generic (addressspace attribute)": [[4, "numba_dpex.kernel_api.AddressSpace.GENERIC"], [7, "numba_dpex.kernel_api.memory_enums.AddressSpace.GENERIC"]], "global (addressspace attribute)": [[4, "numba_dpex.kernel_api.AddressSpace.GLOBAL"], [7, "numba_dpex.kernel_api.memory_enums.AddressSpace.GLOBAL"]], "group (class in numba_dpex.kernel_api)": [[4, "numba_dpex.kernel_api.Group"]], "item (class in numba_dpex.kernel_api)": [[4, "numba_dpex.kernel_api.Item"]], "local (addressspace attribute)": [[4, "numba_dpex.kernel_api.AddressSpace.LOCAL"], [7, "numba_dpex.kernel_api.memory_enums.AddressSpace.LOCAL"]], "memoryorder (class in numba_dpex.kernel_api)": [[4, "numba_dpex.kernel_api.MemoryOrder"]], "memoryscope (class in numba_dpex.kernel_api)": [[4, "numba_dpex.kernel_api.MemoryScope"]], "nditem (class in numba_dpex.kernel_api)": [[4, "numba_dpex.kernel_api.NdItem"]], "ndrange (class in numba_dpex.kernel_api)": [[4, "numba_dpex.kernel_api.NdRange"]], "private (addressspace attribute)": [[4, "numba_dpex.kernel_api.AddressSpace.PRIVATE"], [7, "numba_dpex.kernel_api.memory_enums.AddressSpace.PRIVATE"]], "relaxed (memoryorder attribute)": [[4, "numba_dpex.kernel_api.MemoryOrder.RELAXED"], [7, "numba_dpex.kernel_api.memory_enums.MemoryOrder.RELAXED"]], "release (memoryorder attribute)": [[4, "numba_dpex.kernel_api.MemoryOrder.RELEASE"], [7, "numba_dpex.kernel_api.memory_enums.MemoryOrder.RELEASE"]], "range (class in numba_dpex.kernel_api)": [[4, "numba_dpex.kernel_api.Range"]], "seq_cst (memoryorder attribute)": [[4, "numba_dpex.kernel_api.MemoryOrder.SEQ_CST"], [7, "numba_dpex.kernel_api.memory_enums.MemoryOrder.SEQ_CST"]], "sub_group (memoryscope attribute)": [[4, "numba_dpex.kernel_api.MemoryScope.SUB_GROUP"], [7, "numba_dpex.kernel_api.memory_enums.MemoryScope.SUB_GROUP"]], "system (memoryscope attribute)": [[4, "numba_dpex.kernel_api.MemoryScope.SYSTEM"], [7, "numba_dpex.kernel_api.memory_enums.MemoryScope.SYSTEM"]], "undefined_dimension (range attribute)": [[4, "numba_dpex.kernel_api.Range.UNDEFINED_DIMENSION"], [8, "numba_dpex.kernel_api.ranges.Range.UNDEFINED_DIMENSION"]], "work_group (memoryscope attribute)": [[4, "numba_dpex.kernel_api.MemoryScope.WORK_GROUP"], [7, "numba_dpex.kernel_api.memory_enums.MemoryScope.WORK_GROUP"]], "work_item (memoryscope attribute)": [[4, "numba_dpex.kernel_api.MemoryScope.WORK_ITEM"], [7, "numba_dpex.kernel_api.memory_enums.MemoryScope.WORK_ITEM"]], "call_kernel() (in module numba_dpex.kernel_api)": [[4, "numba_dpex.kernel_api.call_kernel"]], "get() (range method)": [[4, "numba_dpex.kernel_api.Range.get"], [8, "numba_dpex.kernel_api.ranges.Range.get"]], "get_global_id() (nditem method)": [[4, "numba_dpex.kernel_api.NdItem.get_global_id"], [5, "numba_dpex.kernel_api.index_space_ids.NdItem.get_global_id"]], "get_global_linear_id() (nditem method)": [[4, "numba_dpex.kernel_api.NdItem.get_global_linear_id"], [5, "numba_dpex.kernel_api.index_space_ids.NdItem.get_global_linear_id"]], "get_global_range() (nditem method)": [[4, "numba_dpex.kernel_api.NdItem.get_global_range"], [5, "numba_dpex.kernel_api.index_space_ids.NdItem.get_global_range"]], "get_global_range() (ndrange method)": [[4, "numba_dpex.kernel_api.NdRange.get_global_range"], [8, "numba_dpex.kernel_api.ranges.NdRange.get_global_range"]], "get_group() (nditem method)": [[4, "numba_dpex.kernel_api.NdItem.get_group"], [5, "numba_dpex.kernel_api.index_space_ids.NdItem.get_group"]], "get_group_id() (group method)": [[4, "numba_dpex.kernel_api.Group.get_group_id"], [5, "numba_dpex.kernel_api.index_space_ids.Group.get_group_id"]], "get_group_linear_id() (group method)": [[4, "numba_dpex.kernel_api.Group.get_group_linear_id"], [5, "numba_dpex.kernel_api.index_space_ids.Group.get_group_linear_id"]], "get_group_linear_range() (group method)": [[4, "numba_dpex.kernel_api.Group.get_group_linear_range"], [5, "numba_dpex.kernel_api.index_space_ids.Group.get_group_linear_range"]], "get_group_range() (group method)": [[4, "numba_dpex.kernel_api.Group.get_group_range"], [5, "numba_dpex.kernel_api.index_space_ids.Group.get_group_range"]], "get_id() (item method)": [[4, "numba_dpex.kernel_api.Item.get_id"], [5, "numba_dpex.kernel_api.index_space_ids.Item.get_id"]], "get_linear_id() (item method)": [[4, "numba_dpex.kernel_api.Item.get_linear_id"], [5, "numba_dpex.kernel_api.index_space_ids.Item.get_linear_id"]], "get_local_id() (nditem method)": [[4, "numba_dpex.kernel_api.NdItem.get_local_id"], [5, "numba_dpex.kernel_api.index_space_ids.NdItem.get_local_id"]], "get_local_linear_id() (nditem method)": [[4, "numba_dpex.kernel_api.NdItem.get_local_linear_id"], [5, "numba_dpex.kernel_api.index_space_ids.NdItem.get_local_linear_id"]], "get_local_linear_range() (group method)": [[4, "numba_dpex.kernel_api.Group.get_local_linear_range"], [5, "numba_dpex.kernel_api.index_space_ids.Group.get_local_linear_range"]], "get_local_range() (group method)": [[4, "numba_dpex.kernel_api.Group.get_local_range"], [5, "numba_dpex.kernel_api.index_space_ids.Group.get_local_range"]], "get_local_range() (nditem method)": [[4, "numba_dpex.kernel_api.NdItem.get_local_range"], [5, "numba_dpex.kernel_api.index_space_ids.NdItem.get_local_range"]], "get_local_range() (ndrange method)": [[4, "numba_dpex.kernel_api.NdRange.get_local_range"], [8, "numba_dpex.kernel_api.ranges.NdRange.get_local_range"]], "get_range() (item method)": [[4, "numba_dpex.kernel_api.Item.get_range"], [5, "numba_dpex.kernel_api.index_space_ids.Item.get_range"]], "group_barrier() (in module numba_dpex.kernel_api)": [[4, "numba_dpex.kernel_api.group_barrier"]], "numba_dpex.kernel_api": [[4, "module-numba_dpex.kernel_api"]], "size() (range method)": [[4, "numba_dpex.kernel_api.Range.size"], [8, "numba_dpex.kernel_api.ranges.Range.size"]], "group (class in numba_dpex.kernel_api.index_space_ids)": [[5, "numba_dpex.kernel_api.index_space_ids.Group"]], "item (class in numba_dpex.kernel_api.index_space_ids)": [[5, "numba_dpex.kernel_api.index_space_ids.Item"]], "nditem (class in numba_dpex.kernel_api.index_space_ids)": [[5, "numba_dpex.kernel_api.index_space_ids.NdItem"]], "numba_dpex.kernel_api.index_space_ids": [[5, "module-numba_dpex.kernel_api.index_space_ids"]], "call_kernel() (in module numba_dpex.kernel_api.launcher)": [[6, "numba_dpex.kernel_api.launcher.call_kernel"]], "numba_dpex.kernel_api.launcher": [[6, "module-numba_dpex.kernel_api.launcher"]], "addressspace (class in numba_dpex.kernel_api.memory_enums)": [[7, "numba_dpex.kernel_api.memory_enums.AddressSpace"]], "memoryorder (class in numba_dpex.kernel_api.memory_enums)": [[7, "numba_dpex.kernel_api.memory_enums.MemoryOrder"]], "memoryscope (class in numba_dpex.kernel_api.memory_enums)": [[7, "numba_dpex.kernel_api.memory_enums.MemoryScope"]], "numba_dpex.kernel_api.memory_enums": [[7, "module-numba_dpex.kernel_api.memory_enums"]], "ndrange (class in numba_dpex.kernel_api.ranges)": [[8, "numba_dpex.kernel_api.ranges.NdRange"]], "range (class in numba_dpex.kernel_api.ranges)": [[8, "numba_dpex.kernel_api.ranges.Range"]], "numba_dpex.kernel_api.ranges": [[8, "module-numba_dpex.kernel_api.ranges"]], "numba_dpex": [[13, "module-numba_dpex"]], "numba_opt": [[23, "index-0"]], "environment variable": [[23, "index-0"], [28, "index-0"]], "numba_dpex_debuginfo": [[28, "index-0"]]}}) \ No newline at end of file +Search.setIndex({"docnames": ["autoapi/index", "autoapi/numba_dpex/kernel_api/atomic_ref/index", "autoapi/numba_dpex/kernel_api/barrier/index", "autoapi/numba_dpex/kernel_api/flag_enum/index", "autoapi/numba_dpex/kernel_api/index", "autoapi/numba_dpex/kernel_api/index_space_ids/index", "autoapi/numba_dpex/kernel_api/launcher/index", "autoapi/numba_dpex/kernel_api/memory_enums/index", "autoapi/numba_dpex/kernel_api/ranges/index", "contribution_guide", "examples", "getting_started", "glossary", "index", "license", "overview", "programming_model", "release-notes", "useful_links", "user_guide/config", "user_guide/debugging/altering", "user_guide/debugging/backtrace", "user_guide/debugging/breakpoints", "user_guide/debugging/common_issues", "user_guide/debugging/data", "user_guide/debugging/debugging_environment", "user_guide/debugging/features", "user_guide/debugging/frame_info", "user_guide/debugging/index", "user_guide/debugging/limitations", "user_guide/debugging/local_variables", "user_guide/debugging/numba-0.55", "user_guide/debugging/set_up_machine", "user_guide/debugging/stepping", "user_guide/debugging/symbols", "user_guide/dpnp_offload", "user_guide/index", "user_guide/kernel_programming/atomic-operations", "user_guide/kernel_programming/device-functions", "user_guide/kernel_programming/index", "user_guide/kernel_programming/memory_allocation_address_space", "user_guide/kernel_programming/random", "user_guide/kernel_programming/reduction", "user_guide/kernel_programming/supported-python-features", "user_guide/kernel_programming/synchronization", "user_guide/kernel_programming/ufunc", "user_guide/kernel_programming/writing_kernels"], "filenames": ["autoapi/index.rst", "autoapi/numba_dpex/kernel_api/atomic_ref/index.rst", "autoapi/numba_dpex/kernel_api/barrier/index.rst", "autoapi/numba_dpex/kernel_api/flag_enum/index.rst", "autoapi/numba_dpex/kernel_api/index.rst", "autoapi/numba_dpex/kernel_api/index_space_ids/index.rst", "autoapi/numba_dpex/kernel_api/launcher/index.rst", "autoapi/numba_dpex/kernel_api/memory_enums/index.rst", "autoapi/numba_dpex/kernel_api/ranges/index.rst", "contribution_guide.rst", "examples.rst", "getting_started.rst", "glossary.rst", "index.rst", "license.rst", "overview.rst", "programming_model.rst", "release-notes.rst", "useful_links.rst", "user_guide/config.rst", "user_guide/debugging/altering.rst", "user_guide/debugging/backtrace.rst", "user_guide/debugging/breakpoints.rst", "user_guide/debugging/common_issues.rst", "user_guide/debugging/data.rst", "user_guide/debugging/debugging_environment.rst", "user_guide/debugging/features.rst", "user_guide/debugging/frame_info.rst", "user_guide/debugging/index.rst", "user_guide/debugging/limitations.rst", "user_guide/debugging/local_variables.rst", "user_guide/debugging/numba-0.55.rst", "user_guide/debugging/set_up_machine.rst", "user_guide/debugging/stepping.rst", "user_guide/debugging/symbols.rst", "user_guide/dpnp_offload.rst", "user_guide/index.rst", "user_guide/kernel_programming/atomic-operations.rst", "user_guide/kernel_programming/device-functions.rst", "user_guide/kernel_programming/index.rst", "user_guide/kernel_programming/memory_allocation_address_space.rst", "user_guide/kernel_programming/random.rst", "user_guide/kernel_programming/reduction.rst", "user_guide/kernel_programming/supported-python-features.rst", "user_guide/kernel_programming/synchronization.rst", "user_guide/kernel_programming/ufunc.rst", "user_guide/kernel_programming/writing_kernels.rst"], "titles": ["API Reference", "numba_dpex.kernel_api.atomic_ref", "numba_dpex.kernel_api.barrier", "numba_dpex.kernel_api.flag_enum", "numba_dpex.kernel_api", "numba_dpex.kernel_api.index_space_ids", "numba_dpex.kernel_api.launcher", "numba_dpex.kernel_api.memory_enums", "numba_dpex.kernel_api.ranges", "Contribution Guide", "List of examples", "Getting Started", "Glossary", "Data Parallel Extension for Numba*", "License", "Overview", "Programming Model", "Release Notes", "Useful links", "Configuration Options for numba-dpex", "Altering Execution", "Backtrace", "Breakpoints", "Common issues and tips", "Examining Data", "Configure debugging environment", "Supported Features", "Information About a Frame", "Debugging with Intel\u00ae Distribution for GDB*", "Limitations", "Debugging Local Variables", "Debugging Features in Numba 0.55", "Set up the machine for debugging", "Stepping", "Examining the Symbol Table", "Compiling and Offloading dpnp statements", "Tutorials", "Supported Atomic Operations", "Writing Device Functions", "Kernel Programming Basics", "Supported Address Space Qualifiers", "Random Number Generation", "Reduction on SYCL-supported Devices", "Supported Python Features inside numba_dpex.kernel", "Synchronization Functions", "Universal Functions", "Writing Data Parallel Kernels"], "terms": {"thi": [0, 4, 5, 8, 14, 16, 17, 20, 23, 24, 28, 30, 32, 33, 40, 42, 43, 44, 46], "page": [0, 11, 15, 17, 28, 32, 43], "contain": [0, 1, 4, 8, 11], "auto": [0, 16, 23], "gener": [0, 4, 7, 16, 17, 19, 21, 43], "document": [0, 13, 17, 20, 23, 24, 27, 28, 29, 30, 34], "1": [0, 4, 7, 8, 16, 19, 20, 21, 22, 23, 24, 25, 27, 28, 31, 33, 34, 35, 37, 38, 39, 40, 41, 46], "numba_dpex": [0, 11, 13, 15, 16, 17, 19, 20, 21, 22, 23, 24, 25, 27, 28, 30, 31, 33, 34, 35, 36, 37, 38, 39, 40, 42, 44, 46], "kernel_api": [0, 13], "submodul": [0, 17], "overview": [0, 13], "class": [0, 17, 37, 46], "function": [0, 1, 5, 15, 16, 17, 18, 20, 21, 23, 26, 29, 30, 33, 35, 36, 37, 39, 40, 42], "creat": [0, 11, 16, 17, 25, 28, 32, 40, 45], "sphinx": 0, "autoapi": 0, "implement": [1, 4, 5, 6, 7, 15, 16, 17, 18, 32, 37, 38, 40, 42, 44, 46], "mock": [1, 4, 5, 6], "python": [1, 2, 4, 5, 11, 15, 16, 17, 18, 19, 20, 21, 22, 24, 25, 27, 28, 30, 31, 33, 34, 36, 39], "repres": [1, 4, 5, 7, 17, 35, 46], "sycl": [1, 2, 4, 5, 7, 8, 11, 15, 16, 17, 18, 28, 35, 36, 38, 39, 41, 44, 46], "prototyp": [1, 4, 5], "kernel": [1, 4, 5, 6, 8, 13, 16, 17, 19, 20, 21, 22, 23, 24, 25, 27, 28, 30, 31, 33, 34, 35, 36, 38, 40, 42], "befor": [1, 2, 4, 5, 11, 16, 19], "thei": [1, 5, 19, 30, 46], "ar": [1, 2, 4, 5, 8, 11, 14, 15, 16, 17, 19, 27, 28, 30, 32, 33, 35, 37, 39, 40, 43, 45, 46], "jit": [1, 5, 15, 23, 35, 45], "compil": [1, 3, 4, 5, 13, 15, 17, 18, 19, 23, 25, 28, 30, 36, 45], "atomicref": [1, 4], "analogu": [1, 4, 5, 42], "type": [1, 3, 4, 5, 8, 15, 16, 17, 26, 35, 37, 39], "an": [1, 2, 3, 4, 5, 6, 7, 8, 11, 15, 16, 17, 18, 20, 32, 33, 35, 37, 38, 39, 46], "atom": [1, 2, 4, 17, 19, 36, 39], "refer": [1, 4, 7, 11, 13, 15, 16, 17, 22, 23, 28, 30, 40, 45, 46], "i": [1, 2, 4, 6, 7, 8, 11, 14, 15, 16, 17, 19, 20, 21, 22, 24, 25, 27, 28, 29, 30, 31, 32, 33, 34, 35, 37, 38, 39, 40, 41, 42, 44, 45, 46], "ref": [1, 4], "index": [1, 4, 5, 8, 15, 30, 37, 39], "0": [1, 4, 7, 8, 11, 14, 15, 16, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 30, 33, 34, 35, 37, 38, 39, 40, 42, 46], "memory_ord": [1, 4, 7], "memoryord": [1, 4, 7], "relax": [1, 4, 7], "memory_scop": [1, 4], "memoryscop": [1, 2, 4, 7], "devic": [1, 4, 7, 11, 13, 15, 17, 18, 19, 35, 36, 37, 39, 40, 41, 46], "address_spac": [1, 4], "addressspac": [1, 4, 7], "global": [1, 4, 5, 7, 8, 17, 30, 39, 40, 44, 46], "view": [1, 4], "data": [1, 4, 8, 15, 17, 18, 23, 26, 28, 35, 36, 39, 40, 44], "can": [1, 4, 5, 8, 11, 14, 15, 16, 22, 23, 25, 28, 30, 32, 33, 35, 38, 39, 41, 42, 44, 45, 46], "updat": [1, 4, 17, 44], "us": [1, 3, 4, 5, 13, 15, 16, 17, 21, 23, 25, 27, 28, 31, 32, 33, 35, 37, 38, 39, 40, 42, 44, 46], "ani": [1, 2, 4, 11, 16, 21, 40, 42, 43, 44, 46], "fetch_": [1, 4], "member": [1, 3, 4, 5, 7, 8], "fetch_add": [1, 4], "val": [1, 4, 37], "add": [1, 4, 15, 17, 32, 37, 42, 43], "operand": [1, 4], "object": [1, 2, 3, 4, 5, 6, 8, 15, 16, 17, 30, 35, 40, 44, 46], "referenc": [1, 4], "fetch_sub": [1, 4], "subtract": [1, 4, 37], "fetch_min": [1, 4], "calcul": [1, 4], "minimum": [1, 4, 17], "valu": [1, 3, 4, 7, 16, 17, 19, 20, 23, 24, 30, 31, 37, 38, 46], "fetch_max": [1, 4], "maximum": [1, 4], "fetch_and": [1, 4], "bitwis": [1, 4], "AND": [1, 4], "fetch_or": [1, 4], "OR": [1, 4], "fetch_xor": [1, 4], "xor": [1, 4], "load": [1, 4, 17, 25, 34, 37], "store": [1, 4, 16, 37, 42, 44, 46], "exchang": [1, 4], "replac": [1, 4, 17, 35], "compare_exchang": [1, 4], "expect": [1, 4], "desir": [1, 4], "expected_idx": [1, 4], "compar": [1, 4], "assign": [1, 4, 26, 29], "result": [1, 4, 16, 17, 20, 21, 22, 24, 27, 30, 31, 33, 34, 40, 42, 46], "return": [1, 3, 4, 5, 8, 15, 16, 17, 20, 21, 22, 24, 27, 30, 31, 33, 34, 35, 37, 38, 42, 44, 46], "origin": [1, 4, 5], "paramet": [1, 2, 4, 6, 8, 37, 45, 46], "ad": [1, 4, 15, 26, 38, 42], "The": [1, 2, 4, 5, 7, 8, 11, 15, 16, 17, 19, 21, 22, 23, 29, 30, 32, 33, 35, 37, 38, 39, 40, 43, 44, 46], "from": [1, 4, 13, 16, 17, 18, 19, 21, 23, 30, 32, 33, 35, 38, 40, 43, 45, 46], "against": [1, 4], "ANDed": [1, 4], "ORed": [1, 4], "xore": [1, 4], "If": [1, 4, 6, 16, 23, 25, 32, 46], "equal": [1, 4, 16, 30, 46], "otherwis": [1, 4], "arrai": [1, 4, 15, 16, 17, 18, 22, 24, 25, 27, 28, 30, 31, 33, 34, 35, 37, 40, 42, 43, 46], "offset": [1, 4], "where": [1, 4, 16, 21, 22, 30, 46], "present": [1, 4, 16, 21, 35, 37, 45], "true": [1, 4, 15, 16, 21, 22, 25, 27, 28, 30, 33, 34], "comparison": [1, 4], "oper": [1, 2, 4, 16, 17, 18, 36, 39, 43, 44, 46], "were": [1, 4, 16], "success": [1, 4], "simul": 2, "": [2, 4, 8, 15, 16, 17, 19, 28, 40, 45, 46], "primit": 2, "group_barri": [2, 4], "group": [2, 4, 5, 8, 32, 39, 40, 46], "fence_scop": [2, 4], "perform": [2, 4, 16, 17, 18, 37], "across": [2, 4, 16], "all": [2, 4, 5, 8, 11, 14, 16, 17, 28, 30, 32, 34, 35, 40, 44, 46], "work": [2, 4, 5, 8, 16, 17, 20, 25, 28, 29, 31, 32, 39, 40, 44, 45, 46], "item": [2, 4, 5, 8, 16, 39, 40, 44, 46], "index_space_id": [2, 4], "work_group": [2, 4, 7], "model": [2, 4, 13, 15, 17, 35, 39], "after": [2, 4, 11, 15, 16, 30], "It": [2, 4, 8, 11, 15, 16, 23, 30, 31, 39], "synchron": [2, 4, 36, 39], "within": [2, 4, 5, 11, 43], "must": [2, 4, 11, 16, 37, 46], "execut": [2, 4, 5, 8, 15, 16, 19, 23, 26, 28, 33, 35, 39, 41], "construct": [2, 4, 16, 39], "continu": [2, 4, 21, 22, 25, 28, 33, 34], "beyond": [2, 4, 16], "mem": [2, 4, 40], "fenc": [2, 4, 40, 44], "ensur": [2, 4, 11, 16, 23, 33, 41, 44], "memori": [2, 4, 7, 16, 17, 28, 40, 44], "access": [2, 4, 11, 16, 17, 31, 41, 46], "issu": [2, 4, 11, 13, 16, 17, 20, 28, 29], "re": [2, 4, 17, 37], "order": [2, 4, 7, 19, 44], "those": [2, 4, 19, 37], "g": [2, 4, 16, 23, 32], "releas": [2, 4, 7, 11, 13, 32, 42], "prior": [2, 4], "acquir": [2, 4, 7], "afterward": [2, 4], "implicit": [2, 4, 16], "provid": [2, 3, 4, 5, 10, 11, 15, 16, 17, 18, 19, 26, 30, 31, 35, 37, 38, 41, 42, 44, 45], "explicit": [2, 4], "option": [2, 4, 13, 15, 17, 23, 25, 32, 36, 44, 46], "scope": [2, 4, 7, 30], "consist": [2, 4, 7, 8, 17], "flagenum": [3, 4, 7], "help": [3, 17], "distinguish": 3, "intenum": 3, "intend": 3, "integ": [3, 4, 7, 17], "liter": [3, 30], "insid": [3, 13, 17, 23, 28, 36, 39, 40, 46], "infer": [3, 16, 17, 35, 45], "infrastructur": 3, "helper": [3, 16, 17, 44], "should": [3, 11, 16, 20, 22, 29, 32, 40, 42], "consid": [3, 16, 21, 22, 33], "base": [3, 4, 7, 8, 11, 15, 16, 17, 32], "enum": [3, 4, 7], "numba": [3, 10, 11, 14, 15, 18, 20, 22, 23, 24, 25, 26, 27, 28, 34, 35, 36, 37, 38, 39, 40, 41, 42, 44], "basetyp": 3, "dummi": [3, 30], "int": [3, 4, 5, 8, 30, 37, 42, 43, 46], "classmethod": 3, "instanc": [3, 4, 5, 6, 16, 46], "modul": [4, 15, 17, 30, 39], "set": [4, 8, 11, 15, 17, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 30, 31, 34, 35, 41, 43, 44, 45], "analog": [4, 37, 45], "c": [4, 11, 15, 16, 17, 18, 21, 22, 25, 27, 28, 30, 33, 34, 35, 40, 46], "api": [4, 11, 13, 15, 16, 17, 18, 20, 24, 27, 30, 31, 34, 38, 40], "meant": [4, 11, 46], "allow": [4, 15, 16, 17, 28, 33, 35, 37, 40], "like": [4, 11, 17, 18, 31, 33, 38, 45, 46], "pure": 4, "them": 4, "atomic_ref": 4, "barrier": [4, 40, 42, 44], "flag_enum": [4, 7], "launcher": 4, "memory_enum": 4, "rang": [4, 5, 6, 15, 16, 17, 21, 22, 25, 27, 28, 30, 33, 34, 36, 37, 40, 42, 43, 46], "identifi": [4, 5, 40], "nditem": [4, 5], "nd_item": [4, 5], "address": [4, 7, 17, 36, 39, 45], "space": [4, 7, 8, 16, 17, 36, 39], "support": [4, 7, 11, 15, 16, 17, 18, 19, 28, 29, 34, 35, 36, 39, 44, 45, 46], "enumer": [4, 7, 46], "dpcpp": [4, 7, 11, 17], "For": [4, 7, 11, 16, 19, 20, 23, 28, 29, 32, 44, 46], "more": [4, 7, 15, 16, 23, 33, 46], "detail": [4, 7, 15, 16, 30, 32, 45], "pleas": [4, 7, 11, 15, 46], "ndrang": [4, 5, 6, 8, 17, 40, 42, 46], "A": [4, 5, 6, 7, 8, 11, 16, 17, 19, 22, 40, 42, 46], "encapsul": [4, 8], "launch": [4, 6, 8, 16, 17, 25, 46], "structur": [4, 8], "singl": [4, 8, 16, 17, 23, 33], "call_kernel": [4, 6], "kernel_fn": [4, 6], "index_rang": [4, 6], "kernel_arg": [4, 6], "over": [4, 6, 16, 17, 35], "either": [4, 6, 11, 16, 43, 44], "global_rang": [4, 5, 8, 40], "local_rang": [4, 5, 8, 40], "group_rang": [4, 5], "list": [4, 5, 11, 13, 16, 19, 34, 43, 46], "get_group_id": [4, 5, 42, 46], "dim": [4, 5], "nd": [4, 5, 16], "get_group_linear_id": [4, 5], "linear": [4, 5], "version": [4, 5, 11, 27, 31, 32, 39], "get_group_rang": [4, 5], "extent": [4, 5], "number": [4, 5, 8, 16, 22, 39, 46], "get_group_linear_rang": [4, 5], "total": [4, 5, 39, 42, 46], "nd_rang": [4, 5, 8], "get_local_rang": [4, 5, 8], "dimens": [4, 5, 8, 35, 39], "get_local_linear_rang": [4, 5], "specifi": [4, 5, 8, 11, 13, 15, 17, 19, 22, 40, 46], "sinc": [4, 5, 16, 30], "have": [4, 5, 16, 22, 38], "defin": [4, 5, 8, 19, 22, 39], "posit": [4, 5, 6], "id": [4, 5, 16, 32], "along": [4, 5, 8, 11], "local": [4, 5, 7, 11, 16, 17, 25, 26, 28, 32, 39, 40, 42, 44, 46], "uniqu": [4, 5], "mai": [4, 5, 11, 15, 16, 23, 28, 30, 33, 34, 40], "been": [4, 5], "programm": [4, 5], "chosen": [4, 5], "runtim": [4, 5, 11, 15, 16, 17, 32], "each": [4, 5, 8, 19, 28, 39, 40, 42], "point": [4, 5, 16, 17, 18, 19, 22, 35, 44, 46], "get_linear_id": [4, 5], "get": [4, 5, 8, 13, 15, 16, 31, 32, 46], "associ": [4, 5, 16], "get_id": [4, 5], "idx": [4, 5, 37, 46], "specif": [4, 5, 7, 16, 17, 38, 42], "get_rang": [4, 5], "size": [4, 5, 8, 16, 19, 35, 39, 40, 42, 46], "could": [4, 5, 16, 30, 46], "found": [4, 5, 11, 14, 42, 45], "item_bas": [4, 5], "global_item": [4, 5], "local_item": [4, 5], "get_global_id": [4, 5, 15, 16, 21, 22, 25, 27, 28, 30, 33, 34, 38, 40, 42, 46], "get_global_linear_id": [4, 5], "get_local_id": [4, 5, 42, 46], "get_local_linear_id": [4, 5], "get_global_rang": [4, 5, 8], "get_group": [4, 5], "privat": [4, 7, 17, 40], "constant": [4, 7], "2": [4, 7, 8, 14, 20, 21, 22, 24, 25, 27, 28, 31, 33, 34, 35, 38, 39, 40], "3": [4, 7, 8, 16, 20, 21, 22, 24, 27, 28, 31, 33], "4": [4, 7, 8, 24, 39, 40], "kept": [4, 7], "correspond": [4, 7], "consume_unsupport": [4, 7], "acq_rel": [4, 7], "seq_cst": [4, 7], "5": [4, 7, 16, 17, 20, 24, 27, 30, 31, 34], "2020": [4, 7, 8, 40], "section": [4, 7, 8, 21, 23, 42], "8": [4, 7, 17, 24, 27, 30, 32, 39], "work_item": [4, 7], "sub_group": [4, 7], "system": [4, 7, 16, 32], "global_s": [4, 8, 21, 22, 25, 27, 28, 30, 33, 34, 40, 42, 46], "local_s": [4, 8, 46], "well": [4, 8, 11, 16], "pass": [4, 8, 11, 15, 16, 17, 19, 30, 40, 44, 46], "parallel_for": [4, 8, 16], "basic": [4, 8, 13, 15, 28, 36], "two": [4, 8, 17, 21, 42, 44, 46], "one": [4, 8, 11, 16, 17, 42, 46], "other": [4, 8, 11, 15, 17, 21, 26, 40], "mimic": [4, 8], "behavior": [4, 8, 23, 32, 33], "tupl": [4, 8, 43], "abstract": [4, 8], "describ": [4, 8, 16], "element": [4, 8, 16, 24, 37, 42], "buffer": [4, 8, 16, 44], "depend": [4, 8, 11, 16, 17, 23], "dimension": [4, 8, 42, 46], "just": [4, 8, 18], "wrapper": [4, 8], "top": [4, 8, 11, 35, 39], "three": [4, 8, 15, 16, 30, 40], "undefined_dimens": [4, 8], "e": [4, 8, 16, 17, 18, 23, 30, 38, 40], "multipli": [4, 8], "individu": [4, 8, 23], "callabl": [4, 6], "rais": [4, 6, 16, 37, 43], "valueerror": [4, 6], "first": [4, 6, 11, 15, 16, 21, 23, 31, 32, 33, 37], "argument": [4, 6, 11, 15, 16, 17, 20, 26, 27, 28, 34, 40, 44, 46], "second": [4, 6, 16, 21], "collect": 7, "syntact": 7, "design": [8, 15], "line": [8, 17, 22, 23, 30, 31, 33], "spec": 8, "9": [8, 17, 24], "dpex": [10, 11, 13, 14, 15, 17, 20, 21, 22, 24, 25, 26, 27, 28, 29, 30, 31, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 44, 45], "instruct": [10, 18, 33], "dpbench": 10, "sampl": [10, 16, 28, 30, 41], "its": [11, 16, 17, 24, 44], "recommend": [11, 17, 23, 30], "anaconda": [11, 15], "org": 11, "intel": [11, 13, 15, 17, 18, 21, 25, 26, 32, 36, 39, 40], "channel": [11, 17], "latest": [11, 17, 25, 32], "product": [11, 17, 28], "n": [11, 16, 22, 25, 27, 28, 30, 33, 34, 35, 37, 40, 46], "env": [11, 17, 23, 25], "dpnp": [11, 13, 15, 17, 21, 22, 25, 27, 28, 30, 33, 34, 36, 40, 41, 46], "dpctl": [11, 16, 17, 22, 25, 27, 28, 30, 33, 34, 35, 40, 45], "llvm": [11, 17, 19, 26], "spirv": [11, 17, 19], "forg": 11, "To": [11, 15, 16, 20, 23, 24, 28, 32, 33, 34, 38, 41], "try": [11, 30, 43], "out": [11, 16, 23, 28, 30], "bleed": 11, "edg": 11, "tip": [11, 13, 28], "main": [11, 13, 17, 37, 40, 46], "trunk": 11, "dppy": 11, "label": [11, 30], "dev": [11, 16, 17, 25, 32], "setuptool": 11, "scikit": [11, 17], "backend": [11, 37], "step": [11, 16, 17, 23, 26, 28, 30], "environ": [11, 15, 17, 19, 20, 23, 24, 28, 30, 32, 34], "new": [11, 15, 17], "activ": [11, 19, 23, 25, 32], "vendor": [11, 16, 18, 32, 39], "recip": [11, 17], "setup": [11, 17], "py": [11, 17, 19, 20, 21, 22, 24, 25, 27, 28, 30, 31, 33, 34, 37, 42, 45], "As": [11, 15, 30], "necessari": 11, "suggest": 11, "hass": 11, "need": [11, 15, 16, 19, 32, 38, 40, 46], "cmake": 11, "llvmdev": [11, 17], "pytest": [11, 17], "clone": 11, "repositori": 11, "git": [11, 17], "http": [11, 17], "github": [11, 15, 16, 17, 32], "com": [11, 17], "intelpython": [11, 17], "cd": [11, 32], "develop": [11, 16, 17], "dockerfil": [11, 17], "direct": [11, 28], "user": [11, 15, 16, 17, 19, 32, 38, 40], "bundl": 11, "also": [11, 15, 16, 20, 21, 22, 23, 32, 33, 35, 39], "driver": [11, 17, 23, 25, 28, 40, 46], "librari": [11, 15, 16, 18, 25, 34, 35, 39], "ship": 11, "multistag": 11, "which": [11, 16, 17, 30, 33, 37, 39, 44, 45], "mean": [11, 17, 30, 39], "differ": [11, 15, 16, 18, 19, 23, 30, 32, 33, 39], "target": [11, 13, 15, 17, 18, 30, 39, 45], "avail": [11, 13, 15, 17, 19, 30], "most": [11, 23, 35], "ones": [11, 15, 17, 35], "gpu": [11, 15, 16, 17, 32, 35, 41, 46], "builder": [11, 17], "t": [11, 17], "run": [11, 17, 20, 21, 22, 24, 25, 27, 28, 30, 31, 33, 34, 46], "rm": 11, "when": [11, 15, 16, 17, 30, 31, 44], "attempt": [11, 16], "relat": [11, 17], "call": [11, 16, 17, 30, 35, 39, 44, 46], "limit": [11, 20, 36, 38, 45], "bypass": 11, "valid": [11, 17, 19], "credenti": 11, "github_us": 11, "github_password": 11, "arg": [11, 25, 26, 30, 35, 46], "increas": [11, 17, 28], "token": 11, "instead": [11, 16, 17, 23], "password": 11, "behind": [11, 16], "firewal": 11, "proxi": 11, "server": 11, "http_proxi": 11, "https_proxi": 11, "These": 11, "lowercas": 11, "via": [11, 17, 23, 41], "python_vers": 11, "By": 11, "default": [11, 15, 17, 19, 23, 30, 32, 33, 40], "offici": 11, "slim": 11, "debian": 11, "request": [11, 13, 17], "base_imag": 11, "custom": [11, 17, 32], "note": [11, 16, 27], "ubuntu": [11, 17, 32], "follow": [11, 13, 15, 17, 19, 21, 22, 23, 25, 26, 28, 29, 30, 31, 32, 33, 34, 35, 37, 43, 46], "see": [11, 20, 21, 22, 23, 24, 25, 27, 28, 29, 30, 31, 32, 33, 34], "current": [11, 15, 23, 33, 39, 46], "cr_tag": 11, "igc_tag": 11, "cm_tag": 11, "l0_tag": 11, "oneapi_vers": 11, "dpctl_git_branch": 11, "dpctl_git_url": 11, "dpnp_git_branch": 11, "dpnp_git_url": 11, "numba_dpex_git_branch": 11, "numba_dpex_git_url": 11, "cmake_vers": 11, "cmake_version_build": 11, "intel_numpy_vers": 11, "intel_numba_vers": 11, "cython_vers": 11, "scikit_build_vers": 11, "There": [11, 39], "sever": [11, 15, 22, 30, 35], "alreadi": 11, "ideal": 11, "quickli": 11, "ghcr": 11, "io": [11, 17], "numba_dpex_vers": 11, "ha": [11, 15, 16, 20, 29, 33], "requir": [11, 17, 19, 24, 27, 32, 36, 42, 45], "stage": 11, "primarili": 11, "up": [11, 17, 28], "snippet": [11, 35], "20": [11, 19, 22, 30, 34], "py3": 11, "10": [11, 16, 20, 21, 22, 24, 25, 27, 28, 30, 31, 33, 34, 35, 37, 40], "bash": 11, "advis": [11, 16], "verifi": 11, "l": [11, 32, 46], "m": [11, 35], "f": 11, "enabl": [11, 17, 19, 23, 28, 31], "linux": [11, 17, 32], "dri": [11, 32], "howev": [11, 38, 42], "you": [11, 16, 18, 22, 23, 25, 28, 30, 32, 33, 39, 46], "wsl": 11, "dxg": 11, "v": [11, 15, 17], "usr": [11, 32], "lib": [11, 17, 32], "unit": [11, 13, 16, 17, 39], "show": [11, 30, 35], "wai": [11, 15, 18, 22, 39], "pyarg": 11, "how": [11, 16, 18, 21, 39], "featur": [13, 16, 17, 23, 36, 39], "start": [13, 15, 17, 23, 32, 46], "instal": [13, 15, 17, 23, 25, 32], "pre": [13, 17], "built": [13, 17, 30, 35, 39], "conda": [13, 17, 25], "packag": [13, 15, 16, 17], "build": [13, 17], "sourc": [13, 15, 17, 20, 22, 24, 25, 27, 30, 31, 33, 34], "docker": [13, 15], "test": [13, 17, 27, 30, 31, 40, 46], "exampl": [13, 15, 16, 17, 19, 21, 22, 25, 33, 35, 36, 39, 40, 41, 44, 46], "program": [13, 17, 18, 19, 21, 22, 23, 33, 35, 36, 44, 46], "recogn": 13, "offload": [13, 15, 17, 19, 36, 39], "share": [13, 17, 25, 34, 40], "comput": [13, 15, 17, 18, 32, 35, 42, 46], "tutori": 13, "statement": [13, 36, 43], "debug": [13, 17, 19, 20, 21, 22, 24, 26, 27, 33, 34, 36, 41], "distribut": [13, 15, 17, 21, 25, 26, 32, 36], "gdb": [13, 17, 20, 21, 22, 23, 24, 25, 26, 27, 30, 31, 32, 33, 34, 36], "configur": [13, 17, 23, 28, 30, 33, 36], "link": [13, 17, 32], "contribut": [13, 14], "guid": [13, 17, 32], "classif": 13, "cycl": 13, "pull": [13, 17], "code": [13, 15, 16, 17, 18, 20, 22, 23, 24, 27, 28, 30, 31, 33, 34, 35, 39, 41, 46], "guidelin": 13, "benchmark": 13, "jupyt": 13, "notebook": 13, "glossari": 13, "licens": [13, 17, 40], "changelog": 13, "under": [14, 16], "apach": [14, 17, 40], "usag": [14, 17, 35, 36, 37, 39, 40], "project": [14, 15, 17], "subject": 14, "term": [14, 39], "condit": [14, 17, 22, 25, 26, 28, 30, 33, 34], "parallel": [15, 16, 18, 36, 39, 40], "extens": [15, 16, 17, 18, 19, 35, 39, 46], "architectur": [15, 16], "agnost": [15, 39], "front": 15, "end": [15, 16, 30, 32, 46], "numpi": [15, 16, 17, 18, 35, 39, 40, 41, 45, 46], "languag": [15, 19], "open": 15, "part": [15, 28, 39, 42], "ai": 15, "analyt": 15, "toolkit": 15, "cloud": 15, "imag": [15, 44], "learn": [15, 46], "similar": [15, 39, 46], "cuda": [15, 37, 39, 42, 44, 45], "sub": [15, 37, 43], "dpc": [15, 16, 18, 37], "spir": [15, 17], "opencl": [15, 17, 18, 32, 39], "oneapi": [15, 16, 17, 20, 21, 22, 24, 25, 27, 28, 30, 31, 32, 33, 34], "level": [15, 17, 18, 23, 26, 32, 38], "zero": [15, 17, 23, 27, 30, 32, 35, 37, 40, 42], "cpu": [15, 16, 18, 28, 46], "In": [15, 16, 18, 19, 25, 27, 31, 39, 40, 42, 46], "futur": [15, 25, 42], "hardwar": [15, 18, 39], "illustr": 15, "vector": [15, 17, 35, 39, 40, 46], "addit": [15, 17, 33, 37, 42], "written": [15, 42, 46], "import": [15, 16, 17, 21, 22, 25, 27, 28, 30, 33, 34, 35, 40, 46], "def": [15, 16, 20, 21, 22, 24, 25, 27, 28, 30, 31, 33, 34, 35, 37, 38, 40, 42, 46], "vecadd_kernel": 15, "b": [15, 20, 21, 22, 24, 25, 27, 28, 30, 33, 34, 38, 40, 46], "1024": [15, 35], "empty_lik": [15, 16, 17, 21, 22, 33, 35], "print": [15, 17, 20, 21, 22, 25, 26, 27, 28, 30, 31, 33, 34, 35, 37, 40, 46], "abov": 15, "alloc": [15, 16, 17, 40], "input": [15, 16, 17, 35, 46], "subsequ": 15, "determin": [15, 16, 46], "standard": [15, 16, 18, 39], "chang": [15, 32], "keyword": [15, 16, 17], "possibl": [15, 16, 17, 23, 30, 31], "leav": 15, "undefin": 15, "let": [15, 16], "select": [15, 16], "flag": [15, 17, 19], "further": 15, "extend": [15, 17, 26, 30], "njit": [15, 17], "equival": [15, 16, 23, 44], "addition": 15, "prang": [15, 17, 35], "loop": [15, 17, 35, 42], "express": [15, 17, 20, 34, 35, 39], "ndarrai": [15, 17, 35], "unlik": [15, 38, 39], "onli": [15, 16, 17, 38, 39, 44, 45, 46], "convert": [15, 17], "same": [15, 16, 18, 44], "exist": [15, 16, 17], "refactor": [15, 17], "Such": [15, 16, 39, 42], "region": [15, 40], "parallelli": 15, "depict": 15, "vecadd_v1": 15, "vecadd_v2": 15, "vecadd_v3": 15, "shape": [15, 24, 34, 35, 40, 46], "invok": [15, 21, 38, 42, 44, 45], "user_manu": 15, "dpnp_offload": 15, "heterogen": [16, 18], "multipl": [16, 17, 23, 33, 39, 42], "want": [16, 25, 32, 44, 46], "engag": 16, "common": [16, 17, 28], "consum": 16, "grade": 16, "laptop": 16, "integr": [16, 17, 41], "discret": 16, "alongsid": 16, "har": 16, "power": [16, 42], "know": 16, "answer": 16, "kei": [16, 32], "question": 16, "doe": [16, 21, 30, 38, 40, 41, 42], "workload": 16, "applic": [16, 17, 23, 28], "manag": [16, 18, 43], "known": [16, 39], "underli": 16, "get_devic": 16, "interest": 16, "select_gpu_devic": 16, "filter": [16, 17], "selector": 16, "string": [16, 17], "sycldevic": 16, "constructor": [16, 17, 35], "dev_gpu": 16, "dev_cpu": 16, "stand": 16, "alon": 16, "gpu_selector": 16, "select_devic": 16, "dev_gpu_alt": 16, "cpu_selector": 16, "dev_cpu_alt": 16, "select_cpu_devic": 16, "queri": 16, "properi": 16, "name": [16, 17, 22, 25, 30, 40], "maxim": 16, "etc": [16, 32], "we": [16, 37, 42], "digress": 16, "explain": 16, "queue": [16, 17, 39, 44], "unifi": 16, "bring": 16, "portabl": [16, 18, 39], "anoth": [16, 38, 45], "aspect": [16, 19], "inher": 16, "flexibl": 16, "make": [16, 17, 22, 25, 31, 32], "go": [16, 17, 33], "even": 16, "strive": 16, "techniqu": 16, "templat": 16, "metaprogram": 16, "dynam": 16, "polymorph": 16, "special": [16, 17, 38], "dispatch": [16, 17], "dure": [16, 17], "onemkl": [16, 35], "task": 16, "submit": [16, 39], "insert": [16, 30], "graph": 16, "onc": 16, "becom": 16, "whose": 16, "met": 16, "submiss": [16, 17], "therefor": 16, "alwai": [16, 27, 31], "directli": [16, 39], "indic": [16, 17], "q1": 16, "syclqueu": [16, 17, 35], "q2": 16, "nativ": [16, 17, 18, 19], "case": [16, 17, 21], "orchestr": 16, "evalu": [16, 20], "polynomi": 16, "everi": 16, "x": [16, 24, 30, 31, 32, 33, 34, 35, 46], "receiv": [16, 23, 33], "y": [16, 25], "np": [16, 17, 21, 22, 25, 27, 28, 30, 33, 34, 37, 40, 42], "p": 16, "onapi_ext": 16, "offloaded_poly_evalu": 16, "exec_q": 16, "appli": [16, 17], "doubl": [16, 34], "precis": [16, 17], "float": [16, 17, 18, 19, 30, 34, 43], "pointer": [16, 17], "translat": 16, "void": [16, 34], "cpp_offloaded_poly_evalu": 16, "q": [16, 20, 21, 22, 24, 25, 27, 28, 30, 31, 33, 34, 35], "const": [16, 30], "size_t": 16, "malloc": 16, "buf_x": 16, "buf_i": 16, "handler": 16, "cgh": 16, "accessor": 16, "flow": 16, "pattern": [16, 44], "acc_x": 16, "read_onli": 16, "acc_i": 16, "write_onli": 16, "no_init": 16, "lambda": 16, "accx": 16, "acci": 16, "wait": [16, 42, 44], "reader": 16, "excel": 16, "freeli": 16, "book": [16, 18], "our": [16, 17], "write": [16, 17, 18, 35, 36, 39, 42, 44], "numba_dpex_poli": 16, "done": [16, 21, 22, 25, 27, 28, 30, 32, 33, 34, 37, 40], "context": [16, 43], "random": [16, 17, 22, 25, 27, 28, 30, 33, 34, 40, 42], "randn": 16, "6": [16, 17, 24, 30, 39], "device_context": [16, 17, 45], "while": [16, 17, 42], "given": [16, 39, 42], "temporari": [16, 17], "thu": 16, "gpu_dev": 16, "wa": [16, 25], "implicitli": 16, "u": 16, "precompil": 16, "__call__": 16, "method": [16, 17], "sure": 16, "conveni": 16, "interpret": 16, "come": 16, "cost": 16, "copi": [16, 17, 40, 46], "host": [16, 19, 32, 38, 46], "commenc": 16, "some": [16, 30, 37, 44], "back": 16, "complet": 16, "usm": [16, 17], "tensor": [16, 17, 18, 40], "usm_ndarrai": [16, 17], "conform": 16, "dpt": [16, 40, 42], "arang": [16, 21, 22, 33, 37, 40], "1e": [16, 17], "usm_typ": 16, "output": [16, 22, 23, 25, 30, 34, 35, 40, 46], "default_local_s": 16, "unambigu": 16, "both": [16, 46], "sycl_queu": [16, 35], "ambigu": [16, 17], "indeterminateexecutionqueueerror": 16, "explicitli": [16, 30, 42, 46], "migrat": 16, "accomplish": 16, "asarrai": 16, "target_devic": 16, "to_devic": 16, "asnumpi": [16, 40, 46], "automat": [16, 17], "deduct": 16, "consit": 16, "control": [16, 17, 18, 44], "full": [16, 17, 22, 23, 35, 39], "through": [16, 33], "creation": [16, 17], "mandat": 16, "obtain": [16, 46], "earlier": 16, "altern": 16, "readabl": 16, "rational": 16, "guarante": 16, "abl": [16, 39], "correctli": [16, 20, 29, 32], "derefer": 16, "involv": 16, "reus": [16, 17], "without": [16, 17, 23, 33, 34], "rule": 16, "prescrib": 16, "combin": 16, "stipul": 16, "measur": [16, 46], "schedul": [16, 23, 26], "unsam": 16, "except": [16, 17, 43], "sometim": 16, "do": [16, 17, 32], "effici": [16, 23, 33], "heavi": 16, "feel": 16, "free": [16, 18], "file": [16, 17, 19, 22, 25, 30, 32, 34], "reach": [16, 22, 44], "gitter": [16, 17], "encount": 16, "notabl": 17, "format": [17, 19], "keep": 17, "adher": 17, "semant": [17, 44], "dead": 17, "silenc": 17, "cover": 17, "error": [17, 28], "1163": 17, "pin": 17, "ci": 17, "1133": 17, "mangl": 17, "1112": 17, "1143": 17, "initi": 17, "scan": 17, "1128": 17, "1123": 17, "secur": 17, "polici": [17, 30], "1117": 17, "1107": 17, "1116": 17, "1127": 17, "1139": 17, "1140": 17, "renam": 17, "clearli": 17, "1145": 17, "dpnpndarrai": 17, "1118": 17, "1113": 17, "bug": 17, "1068": 17, "774": 17, "caus": [17, 28], "due": 17, "improp": 17, "emul": 17, "1103": 17, "1097": 17, "879": 17, "tool": 17, "1108": 17, "atomic_op": [17, 37], "cl": 17, "numba_dpex_activate_atomics_fp_n": 17, "improv": [17, 31], "overload": 17, "1083": 17, "reduct": [17, 35, 36, 37, 39], "1089": 17, "itanium": 17, "cxx": 17, "abi": 17, "mangler": 17, "1080": 17, "sourcewar": 17, "docstr": 17, "1081": 17, "typo": 17, "messag": 17, "interfac": 17, "1082": 17, "999": 17, "proper": 17, "box": 17, "unbox": 17, "dpjit": [17, 35], "decor": [17, 23, 35, 38, 42, 45], "963": 17, "1064": 17, "1032": 17, "991": 17, "full_lik": 17, "997": 17, "complex64": 17, "complex128": 17, "parfor": 17, "1033": 17, "1035": 17, "config": [17, 19], "constantsizestaticlocalmemorypass": [17, 19], "57": 17, "1030": 17, "1003": 17, "1002": 17, "1054": 17, "1056": 17, "1060": 17, "lower": 17, "happen": [17, 23, 33], "pipelin": [17, 19], "996": 17, "now": [17, 46], "monkei": 17, "patch": 17, "move": [17, 33], "numba_patch": 17, "redesign": 17, "suit": 17, "1018": 17, "1017": 17, "1015": 17, "1036": 17, "1037": 17, "1072": 17, "stride": [17, 24, 34, 42], "1023": 17, "cach": [17, 19], "946": 17, "mul": [17, 43], "1048": 17, "node": 17, "uhd": 17, "1074": 17, "1041": 17, "rename_numpy_functions_pass": 17, "stub": 17, "1025": 17, "1043": 17, "1049": 17, "llvm_spirv": 17, "path": [17, 25, 32], "979": 17, "manual": 17, "workflow": 17, "publish": 17, "repo": 17, "973": 17, "dtype": [17, 21, 22, 25, 27, 28, 30, 33, 34, 35, 37, 40, 42], "deriv": 17, "993": 17, "adjust": 17, "test_window": 17, "rt": 17, "990": 17, "layout": 17, "987": 17, "handl": [17, 43], "arraystruct": 17, "meminfo": [17, 24, 34], "null": 17, "close": [17, 45], "gh": 17, "965": 17, "972": 17, "887": 17, "902": 17, "dpextarget": 17, "empti": [17, 35], "zeros_lik": 17, "ones_lik": [17, 22, 25, 27, 28, 30, 33, 34, 40], "928": 17, "923": 17, "style": 17, "957": 17, "70": 17, "ufunc": [17, 45], "backport": 17, "split": [17, 39], "upstream": 17, "949": 17, "alias": 17, "851": 17, "alia": 17, "lru": 17, "804": 17, "func": [17, 21, 22, 30, 33, 38], "877": 17, "syntax": [17, 34, 46], "888": 17, "pacth": 17, "56": [17, 24, 34], "954": 17, "numba_dpex_dump_kernel_llvm": 17, "dump": [17, 19], "ir": [17, 19, 26, 31], "924": 17, "badg": 17, "chatroom": 17, "919": 17, "small": [17, 39], "script": 17, "copyright": 17, "header": 17, "917": 17, "dpexrt_python": 17, "nrt_meminfo": 17, "demonstr": [17, 35, 40, 42], "826": 17, "clk_global_mem_f": 17, "clk_local_mem_f": 17, "global_mem_f": [17, 44], "local_mem_f": [17, 40, 42, 44], "844": 17, "switch": [17, 19, 21, 33], "836": 17, "usmndarraytyp": 17, "usmndarrai": 17, "typess": 17, "880": 17, "intern": 17, "__sycl_usm_array_interface__": 17, "protocol": 17, "885": 17, "dpexcontext": 17, "dpextypingcontext": 17, "dpexkerneltarget": 17, "dpexkerneltypingcontext": 17, "dpnp_stubs_impl": 17, "953": 17, "mismatch": 17, "warn": 17, "importerror": 17, "925": 17, "827": 17, "858": 17, "linter": 17, "black": 17, "23": [17, 22, 27, 28, 30, 33], "isort": 17, "900": 17, "match": [17, 34, 37], "actual": 17, "904": 17, "rewrit": 17, "regress": 17, "912": 17, "896": 17, "qualnam": 17, "905": 17, "numpy_usm_shar": 17, "841": 17, "llvmlite": 17, "llvmpy": 17, "932": 17, "numba0": 17, "818": 17, "dpnp0": 17, "dpctl0": 17, "798": 17, "crash": 17, "take": [17, 35], "non": [17, 23], "771": 17, "pairwise_dist": [17, 35, 46], "machin": [17, 28, 33], "fp64": 17, "hw": 17, "806": 17, "728": 17, "coverag": 17, "action": 17, "upload": 17, "coveral": 17, "621": 17, "80": 17, "char": 17, "reformat": 17, "631": 17, "ignor": 17, "blame": 17, "632": 17, "numba_support": 17, "numba_vers": 17, "656": 17, "skip_no_numba055": 17, "662": 17, "parameter": 17, "661": 17, "skip_no_opencl_xpu": 17, "skip": [17, 33], "663": 17, "unsupport": [17, 39], "664": 17, "attribut": 17, "629": 17, "640": 17, "665": 17, "669": 17, "598": 17, "filter_str": 17, "miss": 17, "672": 17, "check": [17, 23, 25], "mkl": 17, "648": 17, "codeown": 17, "review": 17, "process": [17, 39], "670": 17, "skip_no_dpnp": 17, "668": 17, "675": 17, "644": 17, "680": 17, "forc": [17, 44], "681": 17, "682": 17, "adopt": 17, "55": [17, 24, 26, 27, 28, 30], "654": 17, "public": [17, 32], "695": 17, "708": 17, "709": 17, "710": 17, "659": 17, "674": 17, "prioriti": 17, "691": 17, "codestyl": 17, "696": 17, "697": 17, "libdpctlsyclinterfac": 17, "so": [17, 23, 30, 32, 33], "707": 17, "search": 17, "703": 17, "712": 17, "pokhodenkosa": 17, "cherri": 17, "pick": 17, "649": 17, "651": 17, "deveice_context": 17, "630": 17, "branch": 17, "610": 17, "deprecationwarn": 17, "pars": 17, "639": 17, "642": 17, "bin": 17, "window": 17, "626": 17, "627": 17, "clang": 17, "icx": 17, "622": 17, "574": 17, "numba_dppy_debug": 17, "578": 17, "preliminari": 17, "master": 17, "583": 17, "pr": 17, "586": 17, "trigger": 17, "tag": 17, "589": 17, "593": 17, "595": 17, "599": 17, "documenat": 17, "land": 17, "diptorupd": 17, "601": 17, "clean": 17, "readm": 17, "604": 17, "restrict": 17, "590": 17, "596": 17, "unskip": 17, "0rc1": 17, "606": 17, "infra": 17, "544": 17, "doc": 17, "about": [17, 26, 28, 46], "variabl": [17, 19, 23, 24, 25, 26, 27, 28, 29, 31, 32, 34, 44], "lifetim": [17, 26, 31], "534": 17, "536": 17, "558": 17, "info": [17, 19, 26], "543": 17, "561": 17, "cov": 17, "xdist": 17, "562": 17, "547": 17, "566": 17, "transform": 17, "command": [17, 21, 22, 24, 28, 30, 31, 32, 33, 34], "568": 17, "524": 17, "dot": 17, "matmul": 17, "565": 17, "older": 17, "backward": 17, "compat": [17, 45], "549": 17, "535": 17, "memcpi": 17, "async": 17, "529": 17, "532": 17, "523": 17, "matrix": [17, 35], "560": 17, "yml": 17, "550": 17, "delet": [17, 30], "unus": 17, "run_test": 17, "sh": [17, 25], "522": 17, "redund": 17, "521": 17, "introduc": [17, 39], "ultilit": 17, "489": 17, "505": 17, "508": 17, "507": 17, "509": 17, "497": 17, "510": 17, "54": 17, "493": 17, "514": 17, "7": [17, 21, 22, 24, 25, 27, 28, 30, 33], "513": 17, "502": 17, "515": 17, "dependeci": 17, "498": 17, "genreat": 17, "dwarf": 17, "symbol": [17, 26, 28], "500": 17, "emiss": [17, 28], "inform": [17, 23, 26, 28], "424": 17, "numba_dppi": 17, "455": 17, "cast": [17, 30], "432": 17, "assert": [17, 43], "466": 17, "opt": 17, "bitcod": 17, "481": 17, "426": 17, "numba_dppy_debuginfo": 17, "460": 17, "nest": [17, 26, 33], "breakpoint": [17, 20, 21, 24, 25, 26, 27, 28, 30, 33, 34], "434": 17, "variou": [17, 30, 35], "479": 17, "474": 17, "475": 17, "480": 17, "477": 17, "468": 17, "450": 17, "463": 17, "421": 17, "eager": 17, "291": 17, "op": 17, "435": 17, "deter": 17, "476": 17, "oneapi_root": [17, 25], "dir": 17, "411": 17, "unquot": 17, "386": 17, "408": 17, "378": 17, "388": 17, "389": 17, "380": 17, "323": 17, "394": 17, "400": 17, "402": 17, "396": 17, "405": 17, "362": 17, "379": 17, "cython": 17, "305": 17, "403": 17, "391": 17, "report": 17, "368": 17, "359": 17, "util": [17, 40, 46], "355": 17, "fail": [17, 23], "353": 17, "cpointer": 17, "339": 17, "optim": [17, 23, 26], "62": 17, "337": 17, "297": 17, "bandit": 17, "264": 17, "375": 17, "53": 17, "279": 17, "inlud": 17, "overrid": 17, "get_ufunc_info": 17, "dppytargetcontext": 17, "367": 17, "374": 17, "cpp": 17, "dpnp_glue": 17, "351": 17, "automerg": 17, "gold": 17, "349": 17, "347": 17, "wih": 17, "309": 17, "344": 17, "340": 17, "334": 17, "333": 17, "correct": [17, 25, 31, 40, 44], "310": 17, "303": 17, "350": 17, "blackschol": 17, "377": 17, "dppy_rt": 17, "393": 17, "390": 17, "346": 17, "leak": 17, "369": 17, "354": 17, "commit": 17, "345": 17, "tabl": [17, 26, 28], "smaller": 17, "308": 17, "306": 17, "subprocess": 17, "check_cal": 17, "269": 17, "modifi": [17, 20, 28], "cc": 17, "dparrai": 17, "linalg": 17, "transcendent": 17, "wheel": 17, "find": 17, "formatt": 17, "52": 17, "don": 17, "incorrect": 17, "standalon": 17, "diagnost": [17, 19], "fallback": 17, "eig": 17, "sum": [17, 37, 40, 42, 46], "max": [17, 42], "min": 17, "pseudo": 17, "site": 17, "till": 17, "gain": 17, "overlaod": 17, "oppos": 17, "previou": [17, 27, 31], "lower_builtin": 17, "dppl": 17, "dppltestcas": 17, "unittest": 17, "testcas": 17, "numba_dppy_": 17, "numba_dppy_save_ir_fil": 17, "numba_dppy_spirv_v": 17, "folder": 17, "No": [17, 25, 27, 30, 31], "cffi": 17, "old": [17, 37], "backup": 17, "includ": 17, "advisor": [17, 18], "profil": [17, 18], "descript": 18, "interchang": 18, "between": [18, 42], "vtune": 18, "analysi": 18, "bottleneck": 18, "leve": 18, "down": 18, "low": 18, "analyz": 18, "advic": 18, "better": 18, "composit": 18, "algorithm": [18, 41], "framework": 18, "ieee": 18, "754": 18, "2019": 18, "arithmet": 18, "essenti": 18, "robust": 18, "numer": 18, "foundat": 18, "conjunct": 18, "time": [18, 27, 30, 32, 42, 46], "mostli": 19, "inherit": 19, "core": 19, "disabl": [19, 23, 28], "prefix": 19, "append": [19, 46], "turn": [19, 23], "save_ir_fil": 19, "numba_dpex_save_ir_fil": 19, "numba_dpex_program": 19, "save": 19, "intermedi": 19, "represent": 19, "spirv_val": 19, "offload_diagnost": 19, "native_fp_atom": 19, "fp": 19, "atomci": 19, "emit": [19, 23], "debuginfo_default": 19, "dump_kernel_llvm": 19, "assembli": 19, "ll": 19, "dump_optim": 19, "enable_cach": 19, "numba_dpex_enable_cach": 19, "off": [19, 23], "cache_s": 19, "debug_cach": 19, "cahc": 19, "mechan": 19, "static_local_mem_pass": 19, "side": [20, 24, 27, 30, 31, 34], "common_loop_bodi": [20, 24, 27, 30, 31, 34], "param_a": [20, 24, 27, 30, 31, 34], "param_b": [20, 24, 27, 30, 31, 34], "param_c": [20, 24, 27, 30, 31, 34], "here": [20, 24, 27, 30, 31, 34, 46], "param_d": [20, 24, 27, 30, 31, 34], "session": [20, 24, 27, 30, 34], "numba_opt": [20, 21, 22, 23, 24, 27, 28, 30, 31, 33, 34], "numba_extend_variable_lifetim": [20, 24, 26, 34], "break": [20, 21, 24, 25, 26, 27, 28, 30, 31, 33, 34], "29": [20, 21, 24, 30, 33, 34], "thread": [20, 21, 22, 23, 24, 25, 27, 28, 30, 31, 33, 34, 40, 44], "hit": [20, 21, 22, 24, 25, 27, 28, 30, 31, 33, 34], "simd": [20, 21, 22, 24, 25, 27, 28, 30, 31, 33, 34], "lane": [20, 21, 22, 24, 25, 27, 28, 30, 31, 33, 34], "__main__": [20, 21, 22, 24, 25, 27, 28, 30, 31, 33, 34, 40], "15": [20, 32], "200": 20, "displai": [21, 24, 26], "summari": 21, "your": [21, 22, 32, 46], "got": 21, "simple_dpex_func": [21, 22, 33], "ndpx": [21, 22, 25, 27, 28, 30, 33, 34, 37, 38, 40, 42, 46], "func_sum": [21, 22, 33], "a_in_func": [21, 22, 33], "b_in_func": [21, 22, 33], "locat": [21, 22, 25, 28, 33, 34, 37], "kernel_sum": [21, 22, 33], "a_in_kernel": [21, 22, 33], "b_in_kernel": [21, 22, 33], "c_in_kernel": [21, 22, 33], "float32": [21, 22, 25, 27, 28, 30, 33, 34, 37, 40], "numa_dpex": 21, "pend": [21, 22, 25, 27, 28, 30, 33, 34], "28": [21, 30], "1073742080": [21, 33], "22": [21, 22, 25, 27, 28, 30, 33, 34], "stop": 22, "whenev": 22, "certain": 22, "place": 22, "simple_sum": [22, 25, 28, 33, 34], "data_parallel_sum": [22, 25, 27, 28, 30, 33, 34], "debugg": [22, 25, 27, 28, 30, 32, 33], "intelgt": 23, "gdbserver": 23, "gt": [23, 43], "igfxdcd": [23, 32], "intelgt_auto_attach_dis": 23, "attach": 23, "companion": [23, 28], "dcd": [23, 28], "heavili": 23, "At": [23, 34], "o3": 23, "export": [23, 25, 28, 32], "mode": [23, 28], "numba_dpex_debuginfo": [23, 28], "fals": 23, "numba_debuginfo": 23, "becaus": [23, 33], "multi": [23, 33, 44], "event": [23, 33], "interfer": [23, 33], "lock": [23, 26], "l1": [24, 27, 30, 34], "5931931659579277": [24, 27, 30], "l2": [24, 27, 30], "22954882979393004": [24, 30], "ptype": [24, 26, 31], "byte": [24, 34], "higher": [24, 27, 30, 32], "0x0": 24, "parent": [24, 34], "nitem": [24, 34], "items": [24, 34], "0x555558461000": 24, "10f": [24, 31], "0x555558461010": 24, "0x555558461020": 24, "var": [25, 30], "neo": [25, 28], "successfulli": 25, "least": [26, 34], "filenam": 26, "linenumb": 26, "cond": 26, "stepi": 26, "next": [26, 27, 28, 30, 35], "frame": [26, 28], "backtrac": [26, 28], "examin": [26, 28], "expr": [26, 31], "whati": [26, 31], "alter": [26, 28], "topic": 26, "complex": [26, 43], "test_info": [27, 30], "test_info_arg": 27, "25": [27, 30, 31], "test_info_loc": 27, "sum_local_var": [27, 30], "uniniti": 27, "000": [27, 30], "repeat": [27, 30, 46], "__ocl_dbg_gid0": [27, 30], "__ocl_dbg_gid1": [27, 30], "__ocl_dbg_gid2": [27, 30], "__ocl_dbg_lid0": [27, 30], "__ocl_dbg_lid1": [27, 30], "__ocl_dbg_lid2": [27, 30], "__ocl_dbg_grid0": [27, 30], "__ocl_dbg_grid1": [27, 30], "__ocl_dbg_grid2": [27, 30], "24": [27, 30], "16": [27, 30], "004": [27, 30], "240": [27, 30], "016xuu": [27, 30], "256wuu": [27, 30], "42949672970": [27, 30], "93825037590528": [27, 30], "4612811918334230528": [27, 30], "unset": 28, "significantli": 28, "consumpt": 28, "larg": 28, "Not": 28, "yet": [28, 42, 45], "relev": 28, "graphic": 28, "bind": 28, "nopython": 28, "stabl": 28, "twice": [28, 33], "influenc": 30, "effect": 30, "26": 30, "9795852899551392": 30, "22986688613891601": 30, "tmp": [30, 35, 46], "kernel_11059955544143858990_e6df1": 30, "dbgelf": 30, "analys": 30, "block": [30, 44], "del": 30, "annot": 30, "21": [30, 32], "1d": [30, 34], "2load_glob": 30, "__init__": 30, "4load_method": 30, "getattr": 30, "attr": 30, "0x7f82b8bae430": 30, "const6": 30, "kw": 30, "vararg": 30, "none": [30, 37, 43], "uint32": 30, "int64": [30, 34, 37], "16binary_subscr": 30, "getitem": 30, "fn": 30, "const18": 30, "float64": [30, 37], "28binary_subscr": 30, "11": 30, "const30": 30, "12": 30, "40binary_add": 30, "const48": 30, "19": [30, 32], "nonetyp": 30, "50return_valu": 30, "last": 30, "shown": 30, "workaround": 30, "expand": 30, "reviv": 30, "until": [30, 44], "sum_local_vars_rev": 30, "0x7fcdf7e8c4c0": 30, "27": 30, "30": [30, 32], "48load_glob": 30, "dpexfunctiontempl": 30, "0x7fce12e5cc40": 30, "52call_funct": 30, "const56": 30, "58return_valu": 30, "93825034429928": 30, "93825034429936": 30, "4599075939470750515": 30, "test_breakpoint": 31, "test_breakpoint_with_condition_by_function_argu": 31, "than": 31, "posibl": 31, "samp": 31, "togeth": 31, "numba_dump_annot": 31, "gpgpu": 32, "video": 32, "18": 32, "fedora": 32, "sle": 32, "sp1": 32, "render": 32, "cento": 32, "31": 32, "administr": 32, "sudo": 32, "root": 32, "privileg": 32, "owner": 32, "renderd": 32, "card": 32, "usermod": 32, "usernam": 32, "19533": 32, "download": 32, "dpkg": 32, "deb": 32, "ld_library_path": 32, "my": 32, "my_active_neo": 32, "client": 32, "icd": 32, "ocl_icd_filenam": 32, "overwrit": 32, "ocl_icd_vendor": 32, "libigdrcl": 32, "libintelocl": 32, "r": [32, 42, 46], "tm": 32, "loader": 32, "modinfo": 32, "remov": 32, "o": [32, 35], "signatur": 32, "below": [33, 40, 46], "forward": 33, "pc": 33, "0x00000000fffeb630": 33, "dpex_func": 33, "regexp": 34, "produc": 34, "lot": 34, "typic": 34, "veri": 34, "long": 34, "regular": [34, 45], "mutabl": 34, "align": 34, "struct": 34, "addrspac": 34, "i64": 34, "drop": 35, "univers": [35, 36, 39], "foo": 35, "sqrt": [35, 43, 46], "naiv": 35, "pairwis": [35, 46], "distanc": [35, 46], "x1": 35, "x2": 35, "d": [35, 46], "na\u00efv": 35, "impl": 35, "euclidean": [35, 46], "x1_row": 35, "x2_row": 35, "x1_col": 35, "float0": 35, "outermost": 35, "j": [35, 46], "exclidean": 35, "k": [35, 46], "qualifi": [36, 39], "ari": 37, "int32": [37, 42], "increment": 37, "Its": 37, "decrement": 37, "atomic_reduct": 37, "notion": 38, "a_device_funct": 38, "another_device_funct": 38, "a_kernel_funct": 38, "normal": [38, 41], "capabl": 38, "concept": 39, "being": 39, "offer": 39, "piec": 39, "bigger": 39, "chunk": 39, "48": 39, "bear": 39, "roc": 39, "proprietari": 39, "declar": 39, "invoc": 39, "disjoint": 40, "pool": 40, "among": 40, "spdx": 40, "filecopyrighttext": 40, "2024": 40, "corpor": 40, "kernel_vector_sum": [40, 46], "a_np": [40, 46], "b_np": [40, 46], "c_np": [40, 46], "assert_equ": [40, 46], "__name__": 40, "static": 40, "private_memori": 40, "intrins": 40, "private_memory_kernel": 40, "preload": 40, "hold": 40, "determinist": 40, "select_default_devic": 40, "arr": 40, "orig": 40, "astyp": 40, "print_device_info": 40, "arr_out": 40, "assert_allclos": 40, "ranf": 41, "random_sampl": 41, "rand": 41, "randint": 41, "random_integ": 41, "beta": 41, "binomi": 41, "chisquar": 41, "exponenti": 41, "gamma": [41, 43], "geometr": 41, "gumbel": 41, "hypergeometr": 41, "laplac": 41, "lognorm": 41, "multinomi": 41, "multivariate_norm": 41, "negative_binomi": 41, "poisson": 41, "rayleigh": 41, "standard_cauchi": 41, "standard_exponenti": 41, "standard_gamma": 41, "standard_norm": 41, "uniform": 41, "weibul": 41, "numba_dpex_debug": 41, "look": 41, "stdout": 41, "approach": 42, "summat": [42, 46], "sum_reduct": 42, "reduc": 42, "sum_reduction_kernel": 42, "nex": 42, "iter": 42, "sum_reduc": 42, "len": [42, 43], "half": 42, "math": [42, 43], "floor": [42, 43], "sum_reduction_recursive_ocl": 42, "input_s": 42, "partial_sum": 42, "local_id": 42, "global_id": 42, "group_siz": 42, "get_local_s": [42, 46], "group_id": 42, "local_sum": 42, "64": 42, "divid": 42, "workgroup": 42, "2x2": 42, "sum_recursive_reduct": 42, "dinp": 42, "dpartial_sum": 42, "nb_work_group": 42, "passed_s": 42, "els": 42, "gr": 42, "lr": 42, "work_group_s": 42, "sum_reduction_ocl": 42, "bool": 43, "ab": 43, "round": 43, "aco": 43, "asin": 43, "atan": 43, "acosh": 43, "asinh": 43, "atanh": 43, "co": 43, "sin": 43, "tan": 43, "cosh": 43, "sinh": 43, "tanh": 43, "erf": 43, "erfc": 43, "exp": 43, "expm1": 43, "fab": 43, "lgamma": 43, "log": 43, "log10": 43, "log1p": 43, "ceil": 43, "eq": 43, "floordiv": 43, "ge": 43, "iadd": 43, "ifloordiv": 43, "imod": 43, "imul": 43, "ipow": 43, "isub": 43, "itruediv": 43, "le": 43, "lshift": 43, "lt": 43, "mod": 43, "ne": 43, "neg": 43, "not_": 43, "or_": 43, "po": 43, "pow": 43, "truediv": 43, "final": 43, "comprehens": 43, "dict": 43, "yield": 43, "whole": 43, "tradit": 44, "caller": 44, "read": 44, "flush": 44, "syncthread": 44, "routin": 45, "although": 45, "fulli": 45, "guvector": 45, "cannot": [45, 46], "ongo": 45, "progress": 45, "blacksholes_njit": 45, "eschew": 45, "fpga": 46, "characterist": 46, "scalar": 46, "pair": 46, "wise": 46, "xshape0": 46, "xshape1": 46, "d0": 46, "total_tim": 46, "get_global_s": 46, "get_num_group": 46}, "objects": {"": [[13, 0, 0, "-", "numba_dpex"]], "numba_dpex": [[4, 0, 0, "-", "kernel_api"]], "numba_dpex.kernel_api": [[4, 1, 1, "", "AddressSpace"], [4, 1, 1, "", "AtomicRef"], [4, 1, 1, "", "Group"], [4, 1, 1, "", "Item"], [4, 1, 1, "", "MemoryOrder"], [4, 1, 1, "", "MemoryScope"], [4, 1, 1, "", "NdItem"], [4, 1, 1, "", "NdRange"], [4, 1, 1, "", "Range"], [1, 0, 0, "-", "atomic_ref"], [2, 0, 0, "-", "barrier"], [4, 4, 1, "", "call_kernel"], [3, 0, 0, "-", "flag_enum"], [4, 4, 1, "", "group_barrier"], [5, 0, 0, "-", "index_space_ids"], [6, 0, 0, "-", "launcher"], [7, 0, 0, "-", "memory_enums"], [8, 0, 0, "-", "ranges"]], "numba_dpex.kernel_api.AddressSpace": [[4, 2, 1, "", "CONSTANT"], [4, 2, 1, "", "GENERIC"], [4, 2, 1, "", "GLOBAL"], [4, 2, 1, "", "LOCAL"], [4, 2, 1, "", "PRIVATE"]], "numba_dpex.kernel_api.AtomicRef": [[4, 3, 1, "", "compare_exchange"], [4, 3, 1, "", "exchange"], [4, 3, 1, "", "fetch_add"], [4, 3, 1, "", "fetch_and"], [4, 3, 1, "", "fetch_max"], [4, 3, 1, "", "fetch_min"], [4, 3, 1, "", "fetch_or"], [4, 3, 1, "", "fetch_sub"], [4, 3, 1, "", "fetch_xor"], [4, 3, 1, "", "load"], [4, 3, 1, "", "store"]], "numba_dpex.kernel_api.Group": [[4, 3, 1, "", "get_group_id"], [4, 3, 1, "", "get_group_linear_id"], [4, 3, 1, "", "get_group_linear_range"], [4, 3, 1, "", "get_group_range"], [4, 3, 1, "", "get_local_linear_range"], [4, 3, 1, "", "get_local_range"]], "numba_dpex.kernel_api.Item": [[4, 3, 1, "", "get_id"], [4, 3, 1, "", "get_linear_id"], [4, 3, 1, "", "get_range"]], "numba_dpex.kernel_api.MemoryOrder": [[4, 2, 1, "", "ACQUIRE"], [4, 2, 1, "", "ACQ_REL"], [4, 2, 1, "", "CONSUME_UNSUPPORTED"], [4, 2, 1, "", "RELAXED"], [4, 2, 1, "", "RELEASE"], [4, 2, 1, "", "SEQ_CST"]], "numba_dpex.kernel_api.MemoryScope": [[4, 2, 1, "", "DEVICE"], [4, 2, 1, "", "SUB_GROUP"], [4, 2, 1, "", "SYSTEM"], [4, 2, 1, "", "WORK_GROUP"], [4, 2, 1, "", "WORK_ITEM"]], "numba_dpex.kernel_api.NdItem": [[4, 3, 1, "", "get_global_id"], [4, 3, 1, "", "get_global_linear_id"], [4, 3, 1, "", "get_global_range"], [4, 3, 1, "", "get_group"], [4, 3, 1, "", "get_local_id"], [4, 3, 1, "", "get_local_linear_id"], [4, 3, 1, "", "get_local_range"]], "numba_dpex.kernel_api.NdRange": [[4, 3, 1, "", "get_global_range"], [4, 3, 1, "", "get_local_range"]], "numba_dpex.kernel_api.Range": [[4, 2, 1, "", "UNDEFINED_DIMENSION"], [4, 3, 1, "", "get"], [4, 3, 1, "", "size"]], "numba_dpex.kernel_api.atomic_ref": [[1, 1, 1, "", "AtomicRef"]], "numba_dpex.kernel_api.atomic_ref.AtomicRef": [[1, 3, 1, "", "compare_exchange"], [1, 3, 1, "", "exchange"], [1, 3, 1, "", "fetch_add"], [1, 3, 1, "", "fetch_and"], [1, 3, 1, "", "fetch_max"], [1, 3, 1, "", "fetch_min"], [1, 3, 1, "", "fetch_or"], [1, 3, 1, "", "fetch_sub"], [1, 3, 1, "", "fetch_xor"], [1, 3, 1, "", "load"], [1, 3, 1, "", "store"]], "numba_dpex.kernel_api.barrier": [[2, 4, 1, "", "group_barrier"]], "numba_dpex.kernel_api.flag_enum": [[3, 1, 1, "", "FlagEnum"]], "numba_dpex.kernel_api.flag_enum.FlagEnum": [[3, 3, 1, "", "basetype"]], "numba_dpex.kernel_api.index_space_ids": [[5, 1, 1, "", "Group"], [5, 1, 1, "", "Item"], [5, 1, 1, "", "NdItem"]], "numba_dpex.kernel_api.index_space_ids.Group": [[5, 3, 1, "", "get_group_id"], [5, 3, 1, "", "get_group_linear_id"], [5, 3, 1, "", "get_group_linear_range"], [5, 3, 1, "", "get_group_range"], [5, 3, 1, "", "get_local_linear_range"], [5, 3, 1, "", "get_local_range"]], "numba_dpex.kernel_api.index_space_ids.Item": [[5, 3, 1, "", "get_id"], [5, 3, 1, "", "get_linear_id"], [5, 3, 1, "", "get_range"]], "numba_dpex.kernel_api.index_space_ids.NdItem": [[5, 3, 1, "", "get_global_id"], [5, 3, 1, "", "get_global_linear_id"], [5, 3, 1, "", "get_global_range"], [5, 3, 1, "", "get_group"], [5, 3, 1, "", "get_local_id"], [5, 3, 1, "", "get_local_linear_id"], [5, 3, 1, "", "get_local_range"]], "numba_dpex.kernel_api.launcher": [[6, 4, 1, "", "call_kernel"]], "numba_dpex.kernel_api.memory_enums": [[7, 1, 1, "", "AddressSpace"], [7, 1, 1, "", "MemoryOrder"], [7, 1, 1, "", "MemoryScope"]], "numba_dpex.kernel_api.memory_enums.AddressSpace": [[7, 2, 1, "", "CONSTANT"], [7, 2, 1, "", "GENERIC"], [7, 2, 1, "", "GLOBAL"], [7, 2, 1, "", "LOCAL"], [7, 2, 1, "", "PRIVATE"]], "numba_dpex.kernel_api.memory_enums.MemoryOrder": [[7, 2, 1, "", "ACQUIRE"], [7, 2, 1, "", "ACQ_REL"], [7, 2, 1, "", "CONSUME_UNSUPPORTED"], [7, 2, 1, "", "RELAXED"], [7, 2, 1, "", "RELEASE"], [7, 2, 1, "", "SEQ_CST"]], "numba_dpex.kernel_api.memory_enums.MemoryScope": [[7, 2, 1, "", "DEVICE"], [7, 2, 1, "", "SUB_GROUP"], [7, 2, 1, "", "SYSTEM"], [7, 2, 1, "", "WORK_GROUP"], [7, 2, 1, "", "WORK_ITEM"]], "numba_dpex.kernel_api.ranges": [[8, 1, 1, "", "NdRange"], [8, 1, 1, "", "Range"]], "numba_dpex.kernel_api.ranges.NdRange": [[8, 3, 1, "", "get_global_range"], [8, 3, 1, "", "get_local_range"]], "numba_dpex.kernel_api.ranges.Range": [[8, 2, 1, "", "UNDEFINED_DIMENSION"], [8, 3, 1, "", "get"], [8, 3, 1, "", "size"]]}, "objtypes": {"0": "py:module", "1": "py:class", "2": "py:attribute", "3": "py:method", "4": "py:function"}, "objnames": {"0": ["py", "module", "Python module"], "1": ["py", "class", "Python class"], "2": ["py", "attribute", "Python attribute"], "3": ["py", "method", "Python method"], "4": ["py", "function", "Python function"]}, "titleterms": {"api": 0, "refer": 0, "numba_dpex": [1, 2, 3, 4, 5, 6, 7, 8, 43, 45], "kernel_api": [1, 2, 3, 4, 5, 6, 7, 8], "atomic_ref": 1, "overview": [1, 2, 3, 4, 5, 6, 7, 8, 15], "class": [1, 3, 4, 5, 7, 8], "method": [1, 3, 4, 5, 8], "barrier": 2, "function": [2, 4, 6, 22, 31, 34, 38, 41, 43, 44, 45, 46], "flag_enum": 3, "submodul": 4, "attribut": [4, 7, 8], "index_space_id": 5, "launcher": 6, "memory_enum": 7, "rang": [8, 35], "contribut": 9, "guid": 9, "classif": 9, "develop": [9, 13], "cycl": 9, "issu": [9, 23], "pull": 9, "request": 9, "code": [9, 29], "guidelin": 9, "unit": 9, "test": [9, 11], "document": [9, 18, 39], "tip": [9, 23], "list": 10, "exampl": [10, 11, 20, 24, 27, 28, 30, 31, 34, 37, 42, 45], "todo": [10, 38], "benchmark": 10, "jupyt": 10, "notebook": 10, "get": 11, "start": 11, "instal": 11, "pre": 11, "built": [11, 43], "conda": 11, "packag": 11, "build": 11, "from": 11, "sourc": 11, "insid": [11, 43, 45], "docker": 11, "us": [11, 18, 29, 30], "imag": 11, "glossari": 12, "data": [13, 16, 24, 31, 34, 46], "parallel": [13, 35, 46], "extens": 13, "numba": [13, 17, 19, 29, 30, 31, 45], "misc": 13, "note": [13, 17], "licens": 14, "main": 15, "featur": [15, 26, 28, 31, 43], "portabl": 15, "kernel": [15, 39, 43, 45, 46], "program": [15, 16, 39], "dpjit": 15, "decor": 15, "model": 16, "recogn": 16, "avail": 16, "devic": [16, 38, 42], "specifi": 16, "offload": [16, 35], "target": 16, "share": 16, "comput": 16, "follow": [16, 39], "releas": 17, "changelog": 17, "0": [17, 31], "21": 17, "4": 17, "2023": 17, "10": 17, "12": 17, "fix": 17, "3": [17, 30], "09": 17, "28": 17, "ad": [17, 31], "chang": 17, "remov": 17, "2": [17, 30, 42, 45], "08": 17, "07": 17, "1": [17, 30, 42, 45], "17": 17, "06": 17, "20": 17, "04": 17, "03": 17, "deprec": 17, "19": 17, "2022": 17, "11": 17, "18": 17, "02": 17, "22": 17, "2021": 17, "30": 17, "15": 17, "16": 17, "25": 17, "14": 17, "05": 17, "27": 17, "26": 17, "13": 17, "2020": 17, "version": 17, "48": 17, "dppy": 17, "june": 17, "29": 17, "link": 18, "companion": [18, 32], "configur": [19, 25], "option": 19, "dpex": 19, "alter": [20, 29], "execut": 20, "assign": 20, "variabl": [20, 30], "backtrac": 21, "breakpoint": [22, 23, 31], "break": 22, "filenam": 22, "linenumb": 22, "cond": 22, "nest": 22, "common": 23, "ar": 23, "hit": 23, "debug": [23, 25, 28, 30, 31, 32], "i": 23, "stabl": 23, "twice": 23, "examin": [24, 34], "print": 24, "expr": 24, "complex": [24, 31, 34], "type": [24, 31, 34, 43], "environ": 25, "support": [26, 37, 40, 41, 42, 43], "inform": 27, "about": 27, "frame": 27, "info": [27, 30, 31, 34], "arg": [27, 31, 34], "local": [27, 30, 31], "intel": 28, "distribut": [28, 41], "gdb": [28, 29], "requir": 28, "usag": [28, 45], "limit": [28, 29], "argument": [29, 31], "modifi": 29, "": 29, "direct": 29, "bind": 29, "nopython": 29, "mode": 29, "optim": 30, "level": 30, "llvm": 30, "lifetim": 30, "ir": 30, "numba_extend_variable_lifetim": [30, 31], "numba_dump_annot": 30, "55": 31, "extend": 31, "condit": 31, "displai": 31, "set": [32, 33], "up": 32, "machin": 32, "graphic": 32, "driver": 32, "neo": 32, "dcd": 32, "step": 33, "stepi": 33, "next": 33, "schedul": 33, "lock": 33, "symbol": 34, "tabl": 34, "whati": 34, "ptype": 34, "compil": 35, "dpnp": 35, "statement": 35, "tutori": 36, "atom": 37, "oper": 37, "full": [37, 42, 45], "write": [38, 46], "basic": [39, 45], "thi": 39, "cover": 39, "chapter": 39, "address": 40, "space": 40, "qualifi": 40, "random": 41, "number": 41, "gener": 41, "simpl": 41, "reduct": 42, "sycl": 42, "python": 43, "standard": 43, "librari": 43, "modul": 43, "unsupport": 43, "construct": 43, "numpi": 43, "synchron": 44, "univers": 45, "call": 45, "vector": 45, "declar": 46, "invoc": 46, "index": 46}, "envversion": {"sphinx.domains.c": 3, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 9, "sphinx.domains.index": 1, "sphinx.domains.javascript": 3, "sphinx.domains.math": 2, "sphinx.domains.python": 4, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "sphinx.ext.todo": 2, "sphinx.ext.intersphinx": 1, "sphinx": 60}, "alltitles": {"API Reference": [[0, "api-reference"]], "numba_dpex.kernel_api.atomic_ref": [[1, "module-numba_dpex.kernel_api.atomic_ref"]], "Overview": [[1, "overview"], [2, "overview"], [3, "overview"], [4, "overview"], [5, "overview"], [6, "overview"], [7, "overview"], [8, "overview"], [15, "id2"]], "Classes": [[1, "id1"], [1, "classes"], [3, "id1"], [3, "classes"], [4, "id1"], [4, "classes"], [5, "id3"], [5, "classes"], [7, "id1"], [7, "classes"], [8, "id1"], [8, "classes"]], "Methods": [[1, "id2"], [3, "id2"], [4, "id3"], [4, "id4"], [4, "id5"], [4, "id6"], [4, "id10"], [4, "id12"], [5, "id4"], [5, "id5"], [5, "id6"], [8, "id3"], [8, "id4"]], "numba_dpex.kernel_api.barrier": [[2, "module-numba_dpex.kernel_api.barrier"]], "Function": [[2, "id1"], [4, "id2"], [6, "id1"]], "Functions": [[2, "functions"], [4, "functions"], [6, "functions"]], "numba_dpex.kernel_api.flag_enum": [[3, "module-numba_dpex.kernel_api.flag_enum"]], "numba_dpex.kernel_api": [[4, "module-numba_dpex.kernel_api"]], "Submodules": [[4, "submodules"]], "Attributes": [[4, "id7"], [4, "id8"], [4, "id9"], [4, "id11"], [7, "id2"], [7, "id3"], [7, "id4"], [8, "id2"]], "numba_dpex.kernel_api.index_space_ids": [[5, "module-numba_dpex.kernel_api.index_space_ids"]], "numba_dpex.kernel_api.launcher": [[6, "module-numba_dpex.kernel_api.launcher"]], "numba_dpex.kernel_api.memory_enums": [[7, "module-numba_dpex.kernel_api.memory_enums"]], "numba_dpex.kernel_api.ranges": [[8, "module-numba_dpex.kernel_api.ranges"]], "Contribution Guide": [[9, "contribution-guide"]], "Classification of Contributions": [[9, "classification-of-contributions"]], "Development Cycle": [[9, "development-cycle"]], "Issues and Pull Requests": [[9, "issues-and-pull-requests"]], "Coding Guidelines": [[9, "coding-guidelines"]], "Unit Testing": [[9, "unit-testing"]], "Documentation": [[9, "documentation"]], "Tips for Developers": [[9, "tips-for-developers"]], "List of examples": [[10, "list-of-examples"]], "Todo": [[10, "id2"], [10, "id3"], [10, "id4"], [38, "id1"]], "Benchmarks": [[10, "benchmarks"]], "Jupyter* Notebooks": [[10, "jupyter-notebooks"]], "Getting Started": [[11, "id2"]], "Installing pre-built conda packages": [[11, "installing-pre-built-conda-packages"]], "Building from source": [[11, "building-from-source"]], "Building inside Docker": [[11, "building-inside-docker"]], "Building": [[11, "building"]], "Using the pre-built images": [[11, "using-the-pre-built-images"]], "Testing": [[11, "testing"]], "Examples": [[11, "examples"]], "Glossary": [[12, "id2"]], "Data Parallel Extension for Numba*": [[13, "id2"]], "Development": [[13, null]], "Misc Notes": [[13, null]], "License": [[14, "id2"]], "Main Features": [[15, "main-features"]], "Portable Kernel Programming": [[15, "portable-kernel-programming"]], "dpjit decorator": [[15, "dpjit-decorator"]], "Programming Model": [[16, "id2"]], "Recognizing available devices": [[16, "recognizing-available-devices"]], "Specifying offload target": [[16, "specifying-offload-target"]], "Data sharing": [[16, "data-sharing"]], "Compute follows data": [[16, "compute-follows-data"]], "Release Notes": [[17, "id2"]], "Changelog": [[17, "changelog"]], "[0.21.4] - 2023-10-12": [[17, "id1"]], "Fixed": [[17, "fixed"], [17, "id3"], [17, "id5"], [17, "id10"], [17, "id14"], [17, "id18"], [17, "id22"], [17, "id26"], [17, "id33"], [17, "id38"], [17, "id45"], [17, "id51"], [17, "id56"], [17, "id58"], [17, "id61"], [17, "id65"], [17, "id67"], [17, "id71"]], "[0.21.3] - 2023-09-28": [[17, "id2"]], "Added": [[17, "added"], [17, "id12"], [17, "id17"], [17, "id20"], [17, "id25"], [17, "id28"], [17, "id31"], [17, "id44"], [17, "id49"], [17, "id53"], [17, "id59"], [17, "id63"], [17, "id69"], [17, "id73"]], "Changed": [[17, "changed"], [17, "id6"], [17, "id9"], [17, "id13"], [17, "id21"], [17, "id29"], [17, "id32"], [17, "id35"], [17, "id37"], [17, "id40"], [17, "id42"], [17, "id47"], [17, "id50"], [17, "id54"], [17, "id64"], [17, "id70"], [17, "id74"]], "Removed": [[17, "removed"], [17, "id7"], [17, "id15"], [17, "id23"], [17, "id55"], [17, "id75"]], "[0.21.2] - 2023-08-07": [[17, "id4"]], "[0.21.1] - 2023-07-17": [[17, "id8"]], "[0.21.0] - 2023-06-17": [[17, "id11"]], "[0.20.1] - 2023-04-07": [[17, "id16"]], "[0.20.0] - 2023-03-06": [[17, "id19"]], "Deprecated": [[17, "deprecated"]], "[0.19.0] - 2022-11-21": [[17, "id24"]], "[0.18.1] - 2022-08-06": [[17, "id27"]], "[0.18.0] - 2022-02-22": [[17, "id30"]], "[0.17.4] - 2021-12-02": [[17, "id34"]], "[0.17.3] - 2021-11-30": [[17, "id36"]], "[0.17.2] - 2021-11-15": [[17, "id39"]], "[0.17.1] - 2021-11-10": [[17, "id41"]], "[0.17.0] - 2021-11-03": [[17, "id43"]], "[0.16.1] - 2021-10-20": [[17, "id46"]], "[0.16.0] - 2021-09-28": [[17, "id48"]], "[0.15.0] - 2021-08-25": [[17, "id52"]], "[0.14.4] - 2021-07-09": [[17, "id57"]], "[0.14.3] - 2021-05-27": [[17, "id60"]], "[0.14.2] - 2021-05-26": [[17, "id62"]], "[0.13.1] - 2021-03-11": [[17, "id66"]], "[0.13.0] - 2021-03-02": [[17, "id68"]], "[0.12.0] - 2020-12-17": [[17, "id72"]], "NUMBA Version 0.48.0 + DPPY Version 0.3.0 (June 29, 2020)": [[17, "numba-version-0-48-0-dppy-version-0-3-0-june-29-2020"]], "Useful links": [[18, "id2"]], "Companion documentation": [[18, "id3"]], "Configuration Options for numba-dpex": [[19, "configuration-options-for-numba-dpex"]], "Altering Execution": [[20, "altering-execution"]], "Assignment to Variables": [[20, "assignment-to-variables"]], "Example": [[20, "example"], [27, "example"], [27, "id4"], [30, "example"], [31, "example"], [34, "example"], [37, "example"]], "Backtrace": [[21, "backtrace"]], "Breakpoints": [[22, "breakpoints"]], "break function": [[22, "break-function"]], "break filename:linenumber": [[22, "break-filename-linenumber"]], "break filename:function": [[22, "break-filename-function"]], "break \u2026 if cond": [[22, "break-if-cond"]], "Breakpoints with nested functions": [[22, "breakpoints-with-nested-functions"]], "Common issues and tips": [[23, "common-issues-and-tips"]], "Breakpoints are not hit": [[23, "breakpoints-are-not-hit"]], "Debugging is not stable": [[23, "debugging-is-not-stable"]], "Breakpoint is hit twice": [[23, "breakpoint-is-hit-twice"]], "Examining Data": [[24, "examining-data"]], "print expr": [[24, "print-expr"]], "Example - Complex Data Types": [[24, "example-complex-data-types"], [34, "example-complex-data-types"]], "Configure debugging environment": [[25, "configure-debugging-environment"]], "Supported Features": [[26, "supported-features"]], "Information About a Frame": [[27, "information-about-a-frame"]], "info args": [[27, "info-args"]], "info locals": [[27, "info-locals"]], "Debugging with Intel\u00ae Distribution for GDB*": [[28, "debugging-with-intel-distribution-for-gdb"]], "Requirements": [[28, "requirements"]], "Example of Intel\u00ae Distribution for GDB* usage": [[28, "example-of-intel-distribution-for-gdb-usage"]], "Features and Limitations": [[28, "features-and-limitations"]], "Limitations": [[29, "limitations"]], "Altering arguments modified in code": [[29, "altering-arguments-modified-in-code"]], "Using Numba\u2019s direct gdb bindings in nopython mode": [[29, "using-numba-s-direct-gdb-bindings-in-nopython-mode"]], "Debugging Local Variables": [[30, "debugging-local-variables"]], "Optimization Level for LLVM": [[30, "optimization-level-for-llvm"]], "Local Variables Lifetime in Numba IR": [[30, "local-variables-lifetime-in-numba-ir"]], "Example 1 - Using NUMBA_EXTEND_VARIABLE_LIFETIMES": [[30, "example-1-using-numba-extend-variable-lifetimes"]], "Example 2 - Using NUMBA_DUMP_ANNOTATION": [[30, "example-2-using-numba-dump-annotation"]], "Example 3 - Using info locals": [[30, "example-3-using-info-locals"]], "Debugging Features in Numba 0.55": [[31, "debugging-features-in-numba-0-55"]], "Added info args": [[31, "added-info-args"]], "Extended info locals": [[31, "extended-info-locals"]], "Breakpoint with condition by function argument": [[31, "breakpoint-with-condition-by-function-argument"]], "Added NUMBA_EXTEND_VARIABLE_LIFETIMES": [[31, "added-numba-extend-variable-lifetimes"]], "Displaying Complex Data Types": [[31, "displaying-complex-data-types"]], "Set up the machine for debugging": [[32, "set-up-the-machine-for-debugging"]], "Graphics driver": [[32, "graphics-driver"]], "NEO driver": [[32, "neo-driver"]], "Debug companion driver (DCD)": [[32, "debug-companion-driver-dcd"]], "Stepping": [[33, "stepping"]], "step": [[33, "step"]], "stepi": [[33, "stepi"]], "next": [[33, "next"]], "set scheduler-locking step": [[33, "set-scheduler-locking-step"]], "Examining the Symbol Table": [[34, "examining-the-symbol-table"]], "info functions": [[34, "info-functions"]], "whatis [arg] and ptype [arg]": [[34, "whatis-arg-and-ptype-arg"]], "Compiling and Offloading dpnp statements": [[35, "compiling-and-offloading-dpnp-statements"]], "Parallel Range": [[35, "parallel-range"]], "Tutorials": [[36, "tutorials"]], "Supported Atomic Operations": [[37, "supported-atomic-operations"]], "Full examples": [[37, "full-examples"], [42, "full-examples"]], "Writing Device Functions": [[38, "writing-device-functions"]], "Kernel Programming Basics": [[39, "kernel-programming-basics"]], "This document will cover the following chapters:": [[39, null]], "Supported Address Space Qualifiers": [[40, "supported-address-space-qualifiers"]], "Random Number Generation": [[41, "random-number-generation"]], "Supported functions": [[41, "supported-functions"]], "Simple random": [[41, "simple-random"]], "Distribution": [[41, "distribution"]], "Reduction on SYCL-supported Devices": [[42, "reduction-on-sycl-supported-devices"]], "Example 1": [[42, "example-1"]], "Example 2": [[42, "example-2"]], "Supported Python Features inside numba_dpex.kernel": [[43, "supported-python-features-inside-numba-dpex-kernel"]], "Built-in types": [[43, "built-in-types"]], "Built-in functions": [[43, "built-in-functions"]], "Standard library modules": [[43, "standard-library-modules"]], "Unsupported Constructs": [[43, "unsupported-constructs"]], "NumPy support": [[43, "numpy-support"]], "Synchronization Functions": [[44, "synchronization-functions"]], "Universal Functions": [[45, "universal-functions"]], "Example 1: Basic Usage": [[45, "example-1-basic-usage"]], "Example 2: Calling numba.vectorize inside a numba_dpex.kernel": [[45, "example-2-calling-numba-vectorize-inside-a-numba-dpex-kernel"]], "Full Examples": [[45, "full-examples"]], "Writing Data Parallel Kernels": [[46, "writing-data-parallel-kernels"]], "Kernel Declaration": [[46, "kernel-declaration"]], "Kernel Invocation": [[46, "kernel-invocation"]], "Kernel Indexing Functions": [[46, "kernel-indexing-functions"]]}, "indexentries": {"atomicref (class in numba_dpex.kernel_api.atomic_ref)": [[1, "numba_dpex.kernel_api.atomic_ref.AtomicRef"]], "compare_exchange() (atomicref method)": [[1, "numba_dpex.kernel_api.atomic_ref.AtomicRef.compare_exchange"], [4, "numba_dpex.kernel_api.AtomicRef.compare_exchange"]], "exchange() (atomicref method)": [[1, "numba_dpex.kernel_api.atomic_ref.AtomicRef.exchange"], [4, "numba_dpex.kernel_api.AtomicRef.exchange"]], "fetch_add() (atomicref method)": [[1, "numba_dpex.kernel_api.atomic_ref.AtomicRef.fetch_add"], [4, "numba_dpex.kernel_api.AtomicRef.fetch_add"]], "fetch_and() (atomicref method)": [[1, "numba_dpex.kernel_api.atomic_ref.AtomicRef.fetch_and"], [4, "numba_dpex.kernel_api.AtomicRef.fetch_and"]], "fetch_max() (atomicref method)": [[1, "numba_dpex.kernel_api.atomic_ref.AtomicRef.fetch_max"], [4, "numba_dpex.kernel_api.AtomicRef.fetch_max"]], "fetch_min() (atomicref method)": [[1, "numba_dpex.kernel_api.atomic_ref.AtomicRef.fetch_min"], [4, "numba_dpex.kernel_api.AtomicRef.fetch_min"]], "fetch_or() (atomicref method)": [[1, "numba_dpex.kernel_api.atomic_ref.AtomicRef.fetch_or"], [4, "numba_dpex.kernel_api.AtomicRef.fetch_or"]], "fetch_sub() (atomicref method)": [[1, "numba_dpex.kernel_api.atomic_ref.AtomicRef.fetch_sub"], [4, "numba_dpex.kernel_api.AtomicRef.fetch_sub"]], "fetch_xor() (atomicref method)": [[1, "numba_dpex.kernel_api.atomic_ref.AtomicRef.fetch_xor"], [4, "numba_dpex.kernel_api.AtomicRef.fetch_xor"]], "load() (atomicref method)": [[1, "numba_dpex.kernel_api.atomic_ref.AtomicRef.load"], [4, "numba_dpex.kernel_api.AtomicRef.load"]], "module": [[1, "module-numba_dpex.kernel_api.atomic_ref"], [2, "module-numba_dpex.kernel_api.barrier"], [3, "module-numba_dpex.kernel_api.flag_enum"], [4, "module-numba_dpex.kernel_api"], [5, "module-numba_dpex.kernel_api.index_space_ids"], [6, "module-numba_dpex.kernel_api.launcher"], [7, "module-numba_dpex.kernel_api.memory_enums"], [8, "module-numba_dpex.kernel_api.ranges"], [13, "module-numba_dpex"]], "numba_dpex.kernel_api.atomic_ref": [[1, "module-numba_dpex.kernel_api.atomic_ref"]], "store() (atomicref method)": [[1, "numba_dpex.kernel_api.atomic_ref.AtomicRef.store"], [4, "numba_dpex.kernel_api.AtomicRef.store"]], "group_barrier() (in module numba_dpex.kernel_api.barrier)": [[2, "numba_dpex.kernel_api.barrier.group_barrier"]], "numba_dpex.kernel_api.barrier": [[2, "module-numba_dpex.kernel_api.barrier"]], "flagenum (class in numba_dpex.kernel_api.flag_enum)": [[3, "numba_dpex.kernel_api.flag_enum.FlagEnum"]], "basetype() (flagenum class method)": [[3, "numba_dpex.kernel_api.flag_enum.FlagEnum.basetype"]], "numba_dpex.kernel_api.flag_enum": [[3, "module-numba_dpex.kernel_api.flag_enum"]], "acquire (memoryorder attribute)": [[4, "numba_dpex.kernel_api.MemoryOrder.ACQUIRE"], [7, "numba_dpex.kernel_api.memory_enums.MemoryOrder.ACQUIRE"]], "acq_rel (memoryorder attribute)": [[4, "numba_dpex.kernel_api.MemoryOrder.ACQ_REL"], [7, "numba_dpex.kernel_api.memory_enums.MemoryOrder.ACQ_REL"]], "addressspace (class in numba_dpex.kernel_api)": [[4, "numba_dpex.kernel_api.AddressSpace"]], "atomicref (class in numba_dpex.kernel_api)": [[4, "numba_dpex.kernel_api.AtomicRef"]], "constant (addressspace attribute)": [[4, "numba_dpex.kernel_api.AddressSpace.CONSTANT"], [7, "numba_dpex.kernel_api.memory_enums.AddressSpace.CONSTANT"]], "consume_unsupported (memoryorder attribute)": [[4, "numba_dpex.kernel_api.MemoryOrder.CONSUME_UNSUPPORTED"], [7, "numba_dpex.kernel_api.memory_enums.MemoryOrder.CONSUME_UNSUPPORTED"]], "device (memoryscope attribute)": [[4, "numba_dpex.kernel_api.MemoryScope.DEVICE"], [7, "numba_dpex.kernel_api.memory_enums.MemoryScope.DEVICE"]], "generic (addressspace attribute)": [[4, "numba_dpex.kernel_api.AddressSpace.GENERIC"], [7, "numba_dpex.kernel_api.memory_enums.AddressSpace.GENERIC"]], "global (addressspace attribute)": [[4, "numba_dpex.kernel_api.AddressSpace.GLOBAL"], [7, "numba_dpex.kernel_api.memory_enums.AddressSpace.GLOBAL"]], "group (class in numba_dpex.kernel_api)": [[4, "numba_dpex.kernel_api.Group"]], "item (class in numba_dpex.kernel_api)": [[4, "numba_dpex.kernel_api.Item"]], "local (addressspace attribute)": [[4, "numba_dpex.kernel_api.AddressSpace.LOCAL"], [7, "numba_dpex.kernel_api.memory_enums.AddressSpace.LOCAL"]], "memoryorder (class in numba_dpex.kernel_api)": [[4, "numba_dpex.kernel_api.MemoryOrder"]], "memoryscope (class in numba_dpex.kernel_api)": [[4, "numba_dpex.kernel_api.MemoryScope"]], "nditem (class in numba_dpex.kernel_api)": [[4, "numba_dpex.kernel_api.NdItem"]], "ndrange (class in numba_dpex.kernel_api)": [[4, "numba_dpex.kernel_api.NdRange"]], "private (addressspace attribute)": [[4, "numba_dpex.kernel_api.AddressSpace.PRIVATE"], [7, "numba_dpex.kernel_api.memory_enums.AddressSpace.PRIVATE"]], "relaxed (memoryorder attribute)": [[4, "numba_dpex.kernel_api.MemoryOrder.RELAXED"], [7, "numba_dpex.kernel_api.memory_enums.MemoryOrder.RELAXED"]], "release (memoryorder attribute)": [[4, "numba_dpex.kernel_api.MemoryOrder.RELEASE"], [7, "numba_dpex.kernel_api.memory_enums.MemoryOrder.RELEASE"]], "range (class in numba_dpex.kernel_api)": [[4, "numba_dpex.kernel_api.Range"]], "seq_cst (memoryorder attribute)": [[4, "numba_dpex.kernel_api.MemoryOrder.SEQ_CST"], [7, "numba_dpex.kernel_api.memory_enums.MemoryOrder.SEQ_CST"]], "sub_group (memoryscope attribute)": [[4, "numba_dpex.kernel_api.MemoryScope.SUB_GROUP"], [7, "numba_dpex.kernel_api.memory_enums.MemoryScope.SUB_GROUP"]], "system (memoryscope attribute)": [[4, "numba_dpex.kernel_api.MemoryScope.SYSTEM"], [7, "numba_dpex.kernel_api.memory_enums.MemoryScope.SYSTEM"]], "undefined_dimension (range attribute)": [[4, "numba_dpex.kernel_api.Range.UNDEFINED_DIMENSION"], [8, "numba_dpex.kernel_api.ranges.Range.UNDEFINED_DIMENSION"]], "work_group (memoryscope attribute)": [[4, "numba_dpex.kernel_api.MemoryScope.WORK_GROUP"], [7, "numba_dpex.kernel_api.memory_enums.MemoryScope.WORK_GROUP"]], "work_item (memoryscope attribute)": [[4, "numba_dpex.kernel_api.MemoryScope.WORK_ITEM"], [7, "numba_dpex.kernel_api.memory_enums.MemoryScope.WORK_ITEM"]], "call_kernel() (in module numba_dpex.kernel_api)": [[4, "numba_dpex.kernel_api.call_kernel"]], "get() (range method)": [[4, "numba_dpex.kernel_api.Range.get"], [8, "numba_dpex.kernel_api.ranges.Range.get"]], "get_global_id() (nditem method)": [[4, "numba_dpex.kernel_api.NdItem.get_global_id"], [5, "numba_dpex.kernel_api.index_space_ids.NdItem.get_global_id"]], "get_global_linear_id() (nditem method)": [[4, "numba_dpex.kernel_api.NdItem.get_global_linear_id"], [5, "numba_dpex.kernel_api.index_space_ids.NdItem.get_global_linear_id"]], "get_global_range() (nditem method)": [[4, "numba_dpex.kernel_api.NdItem.get_global_range"], [5, "numba_dpex.kernel_api.index_space_ids.NdItem.get_global_range"]], "get_global_range() (ndrange method)": [[4, "numba_dpex.kernel_api.NdRange.get_global_range"], [8, "numba_dpex.kernel_api.ranges.NdRange.get_global_range"]], "get_group() (nditem method)": [[4, "numba_dpex.kernel_api.NdItem.get_group"], [5, "numba_dpex.kernel_api.index_space_ids.NdItem.get_group"]], "get_group_id() (group method)": [[4, "numba_dpex.kernel_api.Group.get_group_id"], [5, "numba_dpex.kernel_api.index_space_ids.Group.get_group_id"]], "get_group_linear_id() (group method)": [[4, "numba_dpex.kernel_api.Group.get_group_linear_id"], [5, "numba_dpex.kernel_api.index_space_ids.Group.get_group_linear_id"]], "get_group_linear_range() (group method)": [[4, "numba_dpex.kernel_api.Group.get_group_linear_range"], [5, "numba_dpex.kernel_api.index_space_ids.Group.get_group_linear_range"]], "get_group_range() (group method)": [[4, "numba_dpex.kernel_api.Group.get_group_range"], [5, "numba_dpex.kernel_api.index_space_ids.Group.get_group_range"]], "get_id() (item method)": [[4, "numba_dpex.kernel_api.Item.get_id"], [5, "numba_dpex.kernel_api.index_space_ids.Item.get_id"]], "get_linear_id() (item method)": [[4, "numba_dpex.kernel_api.Item.get_linear_id"], [5, "numba_dpex.kernel_api.index_space_ids.Item.get_linear_id"]], "get_local_id() (nditem method)": [[4, "numba_dpex.kernel_api.NdItem.get_local_id"], [5, "numba_dpex.kernel_api.index_space_ids.NdItem.get_local_id"]], "get_local_linear_id() (nditem method)": [[4, "numba_dpex.kernel_api.NdItem.get_local_linear_id"], [5, "numba_dpex.kernel_api.index_space_ids.NdItem.get_local_linear_id"]], "get_local_linear_range() (group method)": [[4, "numba_dpex.kernel_api.Group.get_local_linear_range"], [5, "numba_dpex.kernel_api.index_space_ids.Group.get_local_linear_range"]], "get_local_range() (group method)": [[4, "numba_dpex.kernel_api.Group.get_local_range"], [5, "numba_dpex.kernel_api.index_space_ids.Group.get_local_range"]], "get_local_range() (nditem method)": [[4, "numba_dpex.kernel_api.NdItem.get_local_range"], [5, "numba_dpex.kernel_api.index_space_ids.NdItem.get_local_range"]], "get_local_range() (ndrange method)": [[4, "numba_dpex.kernel_api.NdRange.get_local_range"], [8, "numba_dpex.kernel_api.ranges.NdRange.get_local_range"]], "get_range() (item method)": [[4, "numba_dpex.kernel_api.Item.get_range"], [5, "numba_dpex.kernel_api.index_space_ids.Item.get_range"]], "group_barrier() (in module numba_dpex.kernel_api)": [[4, "numba_dpex.kernel_api.group_barrier"]], "numba_dpex.kernel_api": [[4, "module-numba_dpex.kernel_api"]], "size() (range method)": [[4, "numba_dpex.kernel_api.Range.size"], [8, "numba_dpex.kernel_api.ranges.Range.size"]], "group (class in numba_dpex.kernel_api.index_space_ids)": [[5, "numba_dpex.kernel_api.index_space_ids.Group"]], "item (class in numba_dpex.kernel_api.index_space_ids)": [[5, "numba_dpex.kernel_api.index_space_ids.Item"]], "nditem (class in numba_dpex.kernel_api.index_space_ids)": [[5, "numba_dpex.kernel_api.index_space_ids.NdItem"]], "numba_dpex.kernel_api.index_space_ids": [[5, "module-numba_dpex.kernel_api.index_space_ids"]], "call_kernel() (in module numba_dpex.kernel_api.launcher)": [[6, "numba_dpex.kernel_api.launcher.call_kernel"]], "numba_dpex.kernel_api.launcher": [[6, "module-numba_dpex.kernel_api.launcher"]], "addressspace (class in numba_dpex.kernel_api.memory_enums)": [[7, "numba_dpex.kernel_api.memory_enums.AddressSpace"]], "memoryorder (class in numba_dpex.kernel_api.memory_enums)": [[7, "numba_dpex.kernel_api.memory_enums.MemoryOrder"]], "memoryscope (class in numba_dpex.kernel_api.memory_enums)": [[7, "numba_dpex.kernel_api.memory_enums.MemoryScope"]], "numba_dpex.kernel_api.memory_enums": [[7, "module-numba_dpex.kernel_api.memory_enums"]], "ndrange (class in numba_dpex.kernel_api.ranges)": [[8, "numba_dpex.kernel_api.ranges.NdRange"]], "range (class in numba_dpex.kernel_api.ranges)": [[8, "numba_dpex.kernel_api.ranges.Range"]], "numba_dpex.kernel_api.ranges": [[8, "module-numba_dpex.kernel_api.ranges"]], "numba_dpex": [[13, "module-numba_dpex"]], "numba_opt": [[23, "index-0"]], "environment variable": [[23, "index-0"], [28, "index-0"]], "numba_dpex_debuginfo": [[28, "index-0"]]}}) \ No newline at end of file