Merge branch 'master' into update-indexing-for-array-api-2024

ndgrigorian · ndgrigorian · commit 682b5987d461 · 2025-04-08T22:27:54.000-07:00
diff --git a/.github/workflows/conda-package.yml b/.github/workflows/conda-package.yml
@@ -26,6 +26,11 @@ jobs:
       matrix:
         python: ['3.9', '3.10', '3.11', '3.12', '3.13']
     steps:
+      - name: Cancel Previous Runs
+        uses: styfle/cancel-workflow-action@85880fa0301c86cca9da44039ee3bb12d3bedbfa # 0.12.1
+        with:
+          access_token: ${{ github.token }}
+
       - uses: actions/checkout@v4.2.2
         with:
           fetch-depth: 0
@@ -82,6 +87,11 @@ jobs:
       matrix:
         python: ['3.9', '3.10', '3.11', '3.12', '3.13']
     steps:
+      - name: Cancel Previous Runs
+        uses: styfle/cancel-workflow-action@85880fa0301c86cca9da44039ee3bb12d3bedbfa # 0.12.1
+        with:
+          access_token: ${{ github.token }}
+
       - uses: actions/checkout@v4.2.2
         with:
           fetch-depth: 0
diff --git a/.github/workflows/generate-docs.yml b/.github/workflows/generate-docs.yml
@@ -58,7 +58,7 @@ jobs:
         if: ${{ !github.event.pull_request || github.event.action != 'closed' }}
         shell: bash -l {0}
         run: |
-          pip install numpy cython setuptools scikit-build cmake sphinx"<7.2" pydot graphviz furo \
+          pip install numpy cython setuptools">=70.1" scikit-build cmake sphinx"<7.2" pydot graphviz furo \
                       sphinxcontrib-programoutput sphinxcontrib-googleanalytics sphinx-design \
                       sphinxcontrib-jsmath sphinx-copybutton sphinxcontrib-spelling \
                       versioneer[toml]==0.29
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -13,6 +13,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 ### Changed
 
 * Support for Boolean data-type is added to `dpctl.tensor.ceil`, `dpctl.tensor.floor`, and `dpctl.tensor.trunc` [gh-2033](https://github.com/IntelPython/dpctl/pull/2033)
+* Changed implementation of `DPCTLPlatform_GetDefaultContext` from using deprecated `ext_oneapi_get_default_context` to `khr_get_default_context` [#2042](https://github.com/IntelPython/dpctl/pull/2042).
 
 ### Fixed
 
@@ -223,7 +224,7 @@ The full list of changes that went into this release are:
 * Fix for crash during testing with open source SYCL bundle by updating CPU RT library used [gh-1762](https://github.com/IntelPython/dpctl/pull/1762)
 * Add missing include to fix build break with newer LLVM [gh-1776](https://github.com/IntelPython/dpctl/pull/1776)
 * Add `#include <utility>` for definition of `std::move` used [gh-1787](https://github.com/IntelPython/dpctl/pull/1787)
-* Change to CMake script to accomodate DPC++ transition from PI to UR architecture [gh-1788](https://github.com/IntelPython/dpctl/pull/1788)
+* Change to CMake script to accommodate DPC++ transition from PI to UR architecture [gh-1788](https://github.com/IntelPython/dpctl/pull/1788)
 * Document `tensor._flags.Flags` class [gh-1794](https://github.com/IntelPython/dpctl/pull/1794)
 * Fix for unreferenced unreleased bug in copy-and-cast code logic [gh-1799](https://github.com/IntelPython/dpctl/pull/1799)
 * Explicitly include headers used in C++ translation units implementing reduction operations [gh-1802](https://github.com/IntelPython/dpctl/pull/1802)
@@ -378,7 +379,7 @@ This release reaches milestone of 100% compliance of `dpctl.tensor` functions wi
 * Added bitwise elementwise functions `dpctl.tensor.bitwise_and`, `dpctl.tensor.bitwise_xor`, `dpctl.tensor.bitwise_or`, `dpctl.tensor.bitwise_invert`
 * Added bitwise shift functions `dpctl.tensor.bitwise_left_shift` and `dpctl.tensor.bitwise_right_shift`.
 * Added `dpctl.tensor.atan2` and `dpctl.tensor.signbit` elementwise functions.
-* Added `dpctl.tensor.minumum` and `dpctl.tensor.maximum` binary elementwise functions.
+* Added `dpctl.tensor.minimum` and `dpctl.tensor.maximum` binary elementwise functions.
 * Supported equality checking and hashing for `dpctl.SyclPlatform`.
 * Implemented `types` property for all unary and binary elementwise functions  [#1361](https://github.com/IntelPython/dpctl/pull/1361)
 * Added `dpctl.tensor.repeat` and `dpctl.tensor.tile` functions.
@@ -523,7 +524,7 @@ This release reaches milestone of 100% compliance of `dpctl.tensor` functions wi
 * Updated supported version of DLPack to 0.8 [#1073](https://github.com/IntelPython/dpctl/pull/1073)
 * Implemented queue cache per context/device pair and deployed it in `dpctl.memory`, `dpctl.tensor.from_dlpack` and `dpctl.tensor` array creation functions [#1076](https://github.com/IntelPython/dpctl/pull/1076), [#1079](https://github.com/IntelPython/dpctl/pull/1079)
 
-* Maintainance, CI work: [#1001](https://github.com/IntelPython/dpctl/pull/1001), [#1009](https://github.com/IntelPython/dpctl/pull/1009), [#1011](https://github.com/IntelPython/dpctl/pull/1011), [#1024](https://github.com/IntelPython/dpctl/pull/1024), [#1030](https://github.com/IntelPython/dpctl/pull/1030), [#1032](https://github.com/IntelPython/dpctl/pull/1032), [#1035](https://github.com/IntelPython/dpctl/pull/1035), [#1037](https://github.com/IntelPython/dpctl/pull/1037), [#1039](https://github.com/IntelPython/dpctl/pull/1039), [#1041](https://github.com/IntelPython/dpctl/pull/1041), [#1045](https://github.com/IntelPython/dpctl/pull/1045), [#1047](https://github.com/IntelPython/dpctl/pull/1047), [#1055](https://github.com/IntelPython/dpctl/pull/1055), [#1057](https://github.com/IntelPython/dpctl/pull/1057), [#1059](https://github.com/IntelPython/dpctl/pull/1059), [#1068](https://github.com/IntelPython/dpctl/pull/1068), [#1070](https://github.com/IntelPython/dpctl/pull/1070), [#1074](https://github.com/IntelPython/dpctl/pull/1074), [#1077](https://github.com/IntelPython/dpctl/pull/1077), [#1078](https://github.com/IntelPython/dpctl/pull/1078), [#1081](https://github.com/IntelPython/dpctl/pull/1081), [#1084](https://github.com/IntelPython/dpctl/pull/1084), [#1085](https://github.com/IntelPython/dpctl/pull/1085), [#1088](https://github.com/IntelPython/dpctl/pull/1088), [#1086](https://github.com/IntelPython/dpctl/pull/1086), [#1092](https://github.com/IntelPython/dpctl/pull/1092), [#1093](https://github.com/IntelPython/dpctl/pull/1093)
+* Maintenance, CI work: [#1001](https://github.com/IntelPython/dpctl/pull/1001), [#1009](https://github.com/IntelPython/dpctl/pull/1009), [#1011](https://github.com/IntelPython/dpctl/pull/1011), [#1024](https://github.com/IntelPython/dpctl/pull/1024), [#1030](https://github.com/IntelPython/dpctl/pull/1030), [#1032](https://github.com/IntelPython/dpctl/pull/1032), [#1035](https://github.com/IntelPython/dpctl/pull/1035), [#1037](https://github.com/IntelPython/dpctl/pull/1037), [#1039](https://github.com/IntelPython/dpctl/pull/1039), [#1041](https://github.com/IntelPython/dpctl/pull/1041), [#1045](https://github.com/IntelPython/dpctl/pull/1045), [#1047](https://github.com/IntelPython/dpctl/pull/1047), [#1055](https://github.com/IntelPython/dpctl/pull/1055), [#1057](https://github.com/IntelPython/dpctl/pull/1057), [#1059](https://github.com/IntelPython/dpctl/pull/1059), [#1068](https://github.com/IntelPython/dpctl/pull/1068), [#1070](https://github.com/IntelPython/dpctl/pull/1070), [#1074](https://github.com/IntelPython/dpctl/pull/1074), [#1077](https://github.com/IntelPython/dpctl/pull/1077), [#1078](https://github.com/IntelPython/dpctl/pull/1078), [#1081](https://github.com/IntelPython/dpctl/pull/1081), [#1084](https://github.com/IntelPython/dpctl/pull/1084), [#1085](https://github.com/IntelPython/dpctl/pull/1085), [#1088](https://github.com/IntelPython/dpctl/pull/1088), [#1086](https://github.com/IntelPython/dpctl/pull/1086), [#1092](https://github.com/IntelPython/dpctl/pull/1092), [#1093](https://github.com/IntelPython/dpctl/pull/1093)
 
 
 ### Fixed
@@ -585,7 +586,7 @@ This release reaches milestone of 100% compliance of `dpctl.tensor` functions wi
 
 ### Added
 
-* Implemented and deployed dedicated kernels for copying with casting [#781](https://github.com/IntelPython/dpctl/781), used in `__setitem__`, implementaion of `asarray`, `dpctl.tensor.copy` functions.
+* Implemented and deployed dedicated kernels for copying with casting [#781](https://github.com/IntelPython/dpctl/781), used in `__setitem__`, implementation of `asarray`, `dpctl.tensor.copy` functions.
 * Implemented dedicated copying kernel for `dpctl.tensor.reshape` function [#810](https://github.com/IntelPython/dpctl/810), added support for `copy` keyword [#807](https://github.com/IntelPython/dpctl/807).
 * Implemented dedicated kernel to copy with casting from `numpy.ndarray` into `dpctl.tensor.usm_ndarray` [#817](https://github.com/IntelPython/dpctl/pull/817).
 
@@ -696,7 +697,7 @@ This release reaches milestone of 100% compliance of `dpctl.tensor` functions wi
 - Add a new C API utility function (`DPCTLDeviceMgr_GetDeviceInfoStr`) to return the device info as a C string object [#620](https://github.com/IntelPython/dpctl/pull/620)
 - New Github workflow to build dpclt with nightly Intel llvm/sycl + drivers [#621](https://github.com/IntelPython/dpctl/pull/621)
 - Always raise SubDeviceCreationError even when sub-device counts are zero [#622](https://github.com/IntelPython/dpctl/pull/622)
-- Updated OpenCL interoprability code to fix build with Intel llvm/sycl bundle [#625](https://github.com/IntelPython/dpctl/pull/625)
+- Updated OpenCL interoperability code to fix build with Intel llvm/sycl bundle [#625](https://github.com/IntelPython/dpctl/pull/625)
 - Enabled use of default platform context extension in SYCL compilers that implement this extension [#627](https://github.com/IntelPython/dpctl/pull/627)
 - Implemented `dpctl.utils.get_execution_queue(queue_seq)` utility to help implementing "compute-follows data" convention for offload target [#632](https://github.com/IntelPython/dpctl/pull/632)
  [#631](https://github.com/IntelPython/dpctl/pull/631)
@@ -987,7 +988,7 @@ supports USM.
 ## [0.4.0] - 2020-11-04
 ### Added
 - Device descriptors "max_compute_units", "max_work_item_dimensions", "max_work_item_sizes", "max_work_group_size", "max_num_sub_groups" and "aspects" for int64 atomics inside dpctl C API and inside the dpctl.SyclDevice class.
-- MemoryUSM* classes moved to `dpctl.memory` module, added support for aligned allocation, added support for `prefetch` and `mem_advise` (sychronous) methods, implemented `copy_to_host`, `copy_from_host` and `copy_from_device` methods, pickling support, and zero-copy interoperability with Python objects which implement `__sycl_usm_array_inerface__` protocol.
+- MemoryUSM* classes moved to `dpctl.memory` module, added support for aligned allocation, added support for `prefetch` and `mem_advise` (synchronous) methods, implemented `copy_to_host`, `copy_from_host` and `copy_from_device` methods, pickling support, and zero-copy interoperability with Python objects which implement `__sycl_usm_array_inerface__` protocol.
 - Helper scripts to generate API documentation for both C API and Python.
 
 ### Fixed
@@ -1072,7 +1073,7 @@ supports USM.
 ### Changed
 - Refactored API to expose a minimal sycl::queue interface.
 - Modify cpu_queues, gpu_queues and active_queues to functions.
-- Change static vectors to static pointers to verctors. It disables call for destructors. Destructors are also call in undefined order.
+- Change static vectors to static pointers to vectors. It disables call for destructors. Destructors are also call in undefined order.
 - Rename package PyDPPL to dpCtl.
 - Use dpcpp.exe on Windows instead of dpcpp-cl.exe deleted in oneAPI beta08.
 
diff --git a/docs/doc_sources/user_guides/dlpack.rst b/docs/doc_sources/user_guides/dlpack.rst
@@ -46,8 +46,8 @@ When sharing USM allocation (of any ``sycl::usm::kind``) with ``void * ptr`` bou
     // Keep in mind, the device may be a sub-device
     const sycl::device &ptr_dev = sycl::get_pointer_device(ptr, ctx);
 
-    #if SYCL_EXT_ONEAPI_DEFAULT_CONTEXT
-    const sycl::context &default_ctx = ptr_dev.get_platform().ext_oneapi_get_default_context();
+    #if SYCL_KHR_DEFAULT_CONTEXT
+    const sycl::context &default_ctx = ptr_dev.get_platform().khr_get_default_context();
     #else
     static_assert(false, "ext_oneapi_default_context extension is required");
     #endif
@@ -106,8 +106,8 @@ Importing DLPack with ``device_type == kDLOneAPI``
     // );
 
     // Get default platform context
-    #if SYCL_EXT_ONEAPI_DEFAULT_CONTEXT
-    const sycl::context &default_ctx = root_device.get_platform().ext_oneapi_get_default_context();
+    #if SYCL_KHR_DEFAULT_CONTEXT
+    const sycl::context &default_ctx = root_device.get_platform().khr_get_default_context();
     #else
     static_assert(false, "ext_oneapi_default_context extension is required");
     #endif
diff --git a/libsyclinterface/source/dpctl_sycl_platform_interface.cpp b/libsyclinterface/source/dpctl_sycl_platform_interface.cpp
@@ -227,17 +227,24 @@ DPCTLPlatform_GetDefaultContext(__dpctl_keep const DPCTLSyclPlatformRef PRef)
 {
     auto P = unwrap<platform>(PRef);
     if (P) {
-#ifdef SYCL_EXT_ONEAPI_DEFAULT_CONTEXT
+#if defined(SYCL_KHR_DEFAULT_CONTEXT) ||                                       \
+    defined(SYCL_EXT_ONEAPI_DEFAULT_CONTEXT)
         try {
-            const auto &default_ctx = P->ext_oneapi_get_default_context();
+            const auto &default_ctx = P->
+#ifdef SYCL_KHR_DEFAULT_CONTEXT
+                                      khr_get_default_context()
+#else
+                                      ext_oneapi_get_default_context()
+#endif // SYCL_KHR_DEFAULT_CONTEXT
+                ;
             return wrap<context>(new context(default_ctx));
         } catch (const std::exception &ex) {
             error_handler(ex, __FILE__, __func__, __LINE__);
             return nullptr;
         }
 #else
         return nullptr;
-#endif
+#endif // SYCL_KHR_DEFAULT_CONTEXT || SYCL_EXT_ONEAPI_DEFAULT_CONTEXT
     }
     else {
         error_handler(
