Merge branch 'main' into cl_khr_unified_svm

Author: bashbaug

.github/workflows/release.yml

@@ -46,7 +46,7 @@ jobs:
             python3 makeSpec -clean -spec khr+ext OUTDIR=out.release -j 5 api c env ext cxx4opencl
 
       - name: Release Specs
-        uses: softprops/action-gh-release@da05d552573ad5aba039eaac05058a918a7bf631 # v2.2.2
+        uses: softprops/action-gh-release@72f2c25fcb47643c292f7107632f7a47c1df5cd8 # v2.3.2
         with:
             draft: true
             files: |

OpenCL_C.txt

@@ -5634,7 +5634,7 @@ endif::cl_khr_fp16[]
 The following table describes the following functions:
 
   * A subset of functions from <<table-builtin-math,Built-in Scalar and Vector
-    Argument Math Functions>> that are defined with the half_ prefix .
+    Argument Math Functions>> that are defined with the half_ prefix.
     These functions are implemented with a minimum of 10-bits of accuracy,
     i.e. the maximum error value \<= 8192 ulp.
   * A subset of functions from <<table-builtin-math,Built-in Scalar and Vector
@@ -6779,7 +6779,7 @@ ifdef::cl_khr_fp16[]
   int *islessgreater*(half _x_, half _y_) +
   short__n__ *islessgreater*(half__n__ _x_, half__n__ _y_)
 endif::cl_khr_fp16[]
-    | Returns the component-wise compare of (_x_ < _y_) \|\| (_x_ > _y_) .
+    | Returns the component-wise compare of (_x_ < _y_) \|\| (_x_ > _y_).
 | |
 | int *isfinite*(float) +
   int__n__ *isfinite*(float__n__) +
@@ -13595,7 +13595,7 @@ host enqueues the first instance of the nd-range kernel (dp_func_A).
 The kernel dp_func_A will launch a kernel (evaluate_dp_work_A) that will
 determine if new nd-range work needs to be performed.
 If new nd-range work does need to be performed, then evaluate_dp_work_A will
-enqueue a new instance of dp_func_A .
+enqueue a new instance of dp_func_A.
 This process is repeated until all the work is completed.
 
 [source,opencl_c]

api/appendix_e.asciidoc

@@ -457,11 +457,11 @@ conformance process:
 
   * {CL_DEVICE_LATEST_CONFORMANCE_VERSION_PASSED}
 
-== Summary of Changes from OpenCL 3.0
+== Summary of Changes to OpenCL 3.0
 
 The first non-experimental version of the OpenCL 3.0 specifications was *v3.0.5*.
 
-Changes from *v3.0.5*:
+Changes from *v3.0.5* to *v3.0.6*:
 
   * Fixed the calculation in "mapping work-items onto an ND-range".
   * Added new extensions:
@@ -474,7 +474,7 @@ Changes from *v3.0.5*:
       ** {cl_khr_subgroup_shuffle_relative_EXT}
       ** {cl_khr_subgroup_clustered_reduce_EXT}
 
-Changes from *v3.0.6*:
+Changes from *v3.0.6* to *v3.0.7*:
 
   * Removed erroneous condition for {CL_INVALID_KERNEL_ARGS}.
   * Fixed the spelling of `-cl-no-signed-zeros`.
@@ -487,15 +487,15 @@ Changes from *v3.0.6*:
       ** {cl_khr_spirv_linkonce_odr_EXT}
       ** {cl_khr_suggested_local_work_size_EXT}
 
-Changes from *v3.0.7*:
+Changes from *v3.0.7* to *v3.0.8*:
 
   * Clarified optionality support for double-precision literals.
   * Removed unnecessary phrase from sub-group mask function descriptions.
   * Added _input_slice_pitch_ error condition for read and write image APIs.
   * Added new extension:
       ** {cl_khr_integer_dot_product_EXT}
 
-Changes from *v3.0.8*:
+Changes from *v3.0.8* to *v3.0.9*:
 
   * Added a missing error condition for {clGetKernelSuggestedLocalWorkSizeKHR}.
   * Clarified requirements for {CL_DEVICE_DOUBLE_FP_CONFIG} prior to OpenCL 2.0.
@@ -504,7 +504,7 @@ Changes from *v3.0.8*:
       ** {cl_khr_integer_dot_product_EXT} (version 2)
       ** {cl_khr_semaphore_EXT} (experimental)
       ** {cl_khr_external_semaphore_EXT} (experimental)
-      ** `cl_khr_external_semaphore_dx_fence` (experimental)
+      ** {cl_khr_external_semaphore_dx_fence_EXT} (experimental)
       ** {cl_khr_external_semaphore_opaque_fd_EXT} (experimental)
       ** {cl_khr_external_semaphore_sync_fd_EXT} (experimental)
       ** {cl_khr_external_semaphore_win32_EXT} (experimental)
@@ -514,7 +514,7 @@ Changes from *v3.0.8*:
       ** {cl_khr_external_memory_opaque_fd_EXT} (experimental)
       ** {cl_khr_external_memory_win32_EXT} (experimental)
 
-Changes from *v3.0.9*:
+Changes from *v3.0.9* to *v3.0.10*:
 
   * Relaxed memory object acquire error checking requirements for OpenGL, EGL, and DirectX interop extensions.
   * Added a missing error condition for {clGetSemaphoreHandleForTypeKHR}.
@@ -526,7 +526,7 @@ Changes from *v3.0.9*:
       ** {cl_khr_expect_assume_EXT}
       ** {cl_khr_command_buffer_EXT} (experimental)
 
-Changes from *v3.0.10*:
+Changes from *v3.0.10* to *v3.0.11*:
 
   * Added a requirement for implementations supporting device-side enqueue to also support program scope global variables.
   * Added missing device scope atomic feature guards to several atomic function overloads.
@@ -540,7 +540,7 @@ Changes from *v3.0.10*:
       ** {cl_khr_subgroup_rotate_EXT}
       ** {cl_khr_work_group_uniform_arithmetic_EXT}
 
-Changes from *v3.0.11*:
+Changes from *v3.0.11* to *v3.0.12*:
 
   * Added a definition for a valid object and requirements for testing for valid objects.
   * Added a maximum limit for the number of arguments supported by a kernel.
@@ -551,7 +551,7 @@ Changes from *v3.0.11*:
   * Added new extension:
       ** {cl_khr_command_buffer_mutable_dispatch_EXT} (experimental)
 
-Changes from *v3.0.12*:
+Changes from *v3.0.12* to *v3.0.13*:
 
   * Fixed the accuracy requirements description for half-precision math functions (those prefixed by `half_`).
   * Clarified that the semaphore type must always be provided when creating a semaphore.
@@ -561,7 +561,7 @@ Changes from *v3.0.12*:
   * Fixed a copy-paste error in the extensions quick reference appendix.
   * Fixed typos and improved formatting consistency in the extensions spec.
 
-Changes from *v3.0.13*:
+Changes from *v3.0.13* to *v3.0.14*:
 
   * Corrected the precision for `cross` and `dot` to be based on `HALF_EPSILON` in {cl_khr_fp16_EXT}, see {khronos-opencl-pr}/893[#893].
   * Added a context query for command-buffers to {cl_khr_command_buffer_EXT}, see {khronos-opencl-pr}/899[#899].
@@ -570,7 +570,7 @@ Changes from *v3.0.13*:
   * Added new extension:
       ** {cl_khr_command_buffer_multi_device_EXT} (experimental)
 
-Changes from *v3.0.14*:
+Changes from *v3.0.14* to *v3.0.15*:
 
   * Clarified which error code should be returned when calling {clCreateBuffer} with a pointer to an SVM allocation that is too small, see {khronos-opencl-pr}/879[#879].
   * Improved capitalization and hyphenation consistency throughout the specs, see {khronos-opencl-pr}/902[#902].
@@ -599,7 +599,7 @@ Changes from *v3.0.14*:
   * {cl_khr_subgroup_rotate_EXT}:
       ** Clarified that only rotating within a subgroup is supported, see {khronos-opencl-pr}/967[#967].
 
-Changes from *v3.0.15*:
+Changes from *v3.0.15* to *v3.0.16*:
 
   * Moved all KHR extension text out of the OpenCL Extension specification and into the main specifications.
     The OpenCL Extension specification will be removed in a subsequent revision.
@@ -623,7 +623,7 @@ Changes from *v3.0.15*:
   * Added new extension:
       ** {cl_khr_kernel_clock_EXT} (experimental)
 
-Changes from *v3.0.16*:
+Changes from *v3.0.16* to *v3.0.17*:
 
   * Clarified the definition of command prerequisites, see {khronos-opencl-pr}/923[#923].
   * Clarified the behavior of {CL_DEVICE_TYPE_DEFAULT} and {CL_DEVICE_TYPE_ALL} for custom devices, see {khronos-opencl-pr}/1117[#1117].
@@ -660,10 +660,10 @@ Changes from *v3.0.16*:
   * {cl_khr_semaphore_EXT}:
       ** Clarified external semaphore behavior, removing references to permanence, see {khronos-opencl-pr}/938[#938].
   * Removed experimental extensions due to lack of implementations and tests, see {khronos-opencl-pr}/1160[#1160].
-      ** `cl_khr_external_semaphore_dx_fence` (experimental)
+      ** {cl_khr_external_semaphore_dx_fence_EXT} (experimental)
       ** `cl_khr_external_memory_dx` (experimental)
 
-Changes from *v3.0.17*:
+Changes from *v3.0.17* to *v3.0.18*:
 
   * Added version 2.0 of the {cl_khr_icd} extension for loader-managed dispatch, see {khronos-opencl-pr}/1005[#1005].
   * Added the {cl_ext_buffer_device_address_EXT} extension, see {khronos-opencl-pr}/1159[#1159].
@@ -688,3 +688,24 @@ Changes from *v3.0.17*:
       ** Improved documentation for {clEnqueueReleaseExternalMemObjectsKHR}, see {khronos-opencl-pr}/1332[#1332].
   * {cl_khr_external_memory_dma_buf_EXT}:
       ** Clarified usage, see {khronos-opencl-pr}/1335[#1335].
+
+Changes from *v3.0.18* to *v3.0.19*:
+
+  * Moved description of restrictions for image kernel arguments to {clSetKernelArg}, see {khronos-opencl-pr}/1346[#1346].
+  * Fixed document linking for several extension APIs and enums, see {khronos-opencl-pr}/1360[#1360].
+  * Fixed a wording inconsistency for device and host timer synchronization, see {khronos-opencl-pr}/1364[#1364].
+  * Clarified the conditions when the global work size may be null or zero, see {khronos-opencl-pr}/1381[#1381].
+  * Switched to the term "experimental" to describe extensions that are subject to change, see {khronos-opencl-pr}/1383[#1383].
+  * Removed specific restrictions for custom devices, see {khronos-opencl-pr}/1388[#1388].
+  * Clarified {CL_FP_FMA} description to avoid ambiguity, see {khronos-opencl-pr}/1391[#1391].
+  * {cl_khr_command_buffer_mutable_dispatch_EXT} (experimental):
+      ** Clarified that the mutable dispatch work dimension may be set to zero to indicate that it is unchanged, see {khronos-opencl-pr}/1395[#1395].
+  * {cl_khr_external_semaphore_EXT}:
+      ** Clarified semaphore behavior when payloads are required, see {khronos-opencl-pr}/1362[#1362].
+  * Re-added a previously removed experimental extension, see {khronos-opencl-pr}/1359[#1359].
+      ** {cl_khr_external_semaphore_dx_fence_EXT} (experimental)
+  * The following extension has been finalized and is no longer experimental:
+      ** {cl_khr_kernel_clock_EXT}
+  * Added new extensions:
+      ** {cl_khr_external_memory_android_hardware_buffer_EXT}
+      ** {cl_khr_spirv_queries_EXT}

api/cl_khr_command_buffer.asciidoc

@@ -3,16 +3,14 @@
 
 include::{generated}/meta/{refprefix}cl_khr_command_buffer.txt[]
 
-// *Revision*::
-//    0.9.6
 // *Extension and Version Dependencies*::
 //     This extension requires OpenCL 1.2 or later.
 //     Buffering of SVM commands requires OpenCL 2.0 or later.
 
 === Other Extension Metadata
 
 *Last Modified Date*::
-    2024-12-13
+    2025-07-10
 *IP Status*::
     No known IP claims.
 *Contributors*::
@@ -124,14 +122,6 @@ There are no gurantees made around the values of sync-points returned from
 adding commands to a command-buffer. Any semantics that a could be inferred
 from the sync-point values returned is implementation defined.
 
-==== Simultaneous Use
-
-The optional simultaneous use capability was added to the extension so that
-vendors can support pipelined workflows, where command-buffers are repeatedly
-enqueued without blocking in user code. However, simultaneous use may result in
-command-buffers being more expensive to enqueue than in a sequential model, so
-the capability is optional to enable optimizations on command-buffer recording.
-
 === Interactions With Other Extensions
 
 The introduction of the command-buffer abstraction enables functionality
@@ -242,11 +232,8 @@ features:
   * {cl_device_command_buffer_capabilities_khr_TYPE}
   ** {CL_COMMAND_BUFFER_CAPABILITY_KERNEL_PRINTF_KHR}
   ** {CL_COMMAND_BUFFER_CAPABILITY_DEVICE_SIDE_ENQUEUE_KHR}
-  ** {CL_COMMAND_BUFFER_CAPABILITY_SIMULTANEOUS_USE_KHR}
   * {cl_command_buffer_properties_khr_TYPE}
   ** {CL_COMMAND_BUFFER_FLAGS_KHR}
-  * {cl_command_buffer_flags_khr_TYPE}
-  ** {CL_COMMAND_BUFFER_SIMULTANEOUS_USE_KHR}
   * {cl_command_buffer_info_khr_TYPE}
   ** {CL_COMMAND_BUFFER_QUEUES_KHR}
   ** {CL_COMMAND_BUFFER_NUM_QUEUES_KHR}
@@ -257,7 +244,6 @@ features:
   * {cl_command_buffer_state_khr_TYPE}
   ** {CL_COMMAND_BUFFER_STATE_RECORDING_KHR}
   ** {CL_COMMAND_BUFFER_STATE_EXECUTABLE_KHR}
-  ** {CL_COMMAND_BUFFER_STATE_PENDING_KHR}
   * {cl_command_type_TYPE}
   ** {CL_COMMAND_COMMAND_BUFFER_KHR}
   * New Error Codes
@@ -470,3 +456,6 @@ features:
   * 0.9.7, 2024-12-13
   ** Refactor queue compatability between command-buffer creation and enqueue
      (experimental).
+  * 0.9.8, 2025-07-10
+  ** Rework simultaneous use definition and remove pending state
+     (experimental).

api/cl_khr_command_buffer_mutable_dispatch.asciidoc

@@ -6,7 +6,7 @@ include::{generated}/meta/{refprefix}cl_khr_command_buffer_mutable_dispatch.txt[
 === Other Extension Metadata
 
 *Last Modified Date*::
-    2024-09-05
+    2025-08-08
 *IP Status*::
     No known IP claims.
 *Contributors*::
@@ -41,6 +41,15 @@ This allows inputs and outputs to the kernel, as well as work-item sizes and
 offsets, to change without having to re-record the entire command sequence
 in a new command-buffer.
 
+==== Simultaneous Use
+
+The optional <<simultaneous-use, simultaneous use>> capability was added to the
+extension so that vendors could support concurrent execution of the same
+command-buffer object which has been updated between submissions. However,
+simultaneous use may result in command-buffers having a larger overhead to
+implement, so the capability is optional to enable optimizations when this
+usage isn't required by a user.
+
 === Interactions With Other Extensions
 
 The {clUpdateMutableCommandsKHR} entry-point has been designed for the purpose
@@ -72,6 +81,8 @@ void pointer using {cl_command_buffer_update_type_khr_TYPE}.
 
   * {cl_device_info_TYPE}
   ** {CL_DEVICE_MUTABLE_DISPATCH_CAPABILITIES_KHR}
+  * {cl_device_command_buffer_capabilities_khr_TYPE}
+  ** {CL_COMMAND_BUFFER_CAPABILITY_SIMULTANEOUS_USE_KHR}
   * {cl_command_properties_khr_TYPE}
   ** {CL_MUTABLE_DISPATCH_ASSERTS_KHR}
   ** {CL_MUTABLE_DISPATCH_UPDATABLE_FIELDS_KHR}
@@ -95,6 +106,7 @@ void pointer using {cl_command_buffer_update_type_khr_TYPE}.
   ** {CL_MUTABLE_COMMAND_COMMAND_TYPE_KHR}
   * {cl_command_buffer_flags_khr_TYPE}
   ** {CL_COMMAND_BUFFER_MUTABLE_KHR}
+  ** {CL_COMMAND_BUFFER_SIMULTANEOUS_USE_KHR}
   * {cl_command_buffer_properties_khr_TYPE}
   ** {CL_COMMAND_BUFFER_MUTABLE_DISPATCH_ASSERTS_KHR}
   * {cl_command_buffer_update_type_khr_TYPE}
@@ -363,3 +375,7 @@ may be a introduced as a stand alone extension.
   * Revision 0.9.3, 2024-09-05
   ** Rename `CL_MUTABLE_DISPATCH_PROPERTIES_ARRAY_KHR` to
      `CL_MUTABLE_COMMAND_PROPERTIES_ARRAY_KHR` (experimental).
+  * Revision 0.9.4, 2025-08-08
+    **  Move `CL_COMMAND_BUFFER_SIMULTANEOUS_USE_KHR` and
+        `CL_COMMAND_BUFFER_CAPABILITY_SIMULTANEOUS_USE_KHR` in this
+        extension from the base extension (experimental).