[NFC] Whitespace fixes in yml files

Trim trailing whitespace in the yml files. This also affected some
source files because our generation system assumes a line ending with
a space means to insert a line break on the word before (which I assume
is a bug).

Author: RossBrunton

include/ur_api.h

@@ -1298,10 +1298,8 @@ typedef enum ur_platform_backend_t {
 #endif
 ///////////////////////////////////////////////////////////////////////////////
 #ifndef UR_DEVICE_BINARY_TARGET_UNKNOWN
-/// @brief Target identification strings for
-///        ::ur_device_binary_t.pDeviceTargetSpec
-///        A device type represented by a particular target triple requires
-///        specific
+/// @brief Target identification strings for ::ur_device_binary_t.pDeviceTargetSpec
+///        A device type represented by a particular target triple requires specific
 ///        binary images. We need to map the image type onto the device target triple
 #define UR_DEVICE_BINARY_TARGET_UNKNOWN "<unknown>"
 #endif // UR_DEVICE_BINARY_TARGET_UNKNOWN
@@ -1824,8 +1822,7 @@ typedef enum ur_device_affinity_domain_flag_t {
                                                                    ///< ::UR_DEVICE_AFFINITY_DOMAIN_FLAG_NUMA,
                                                                    ///< ::UR_DEVICE_AFFINITY_DOMAIN_FLAG_L4_CACHE,
                                                                    ///< ::UR_DEVICE_AFFINITY_DOMAIN_FLAG_L3_CACHE,
-                                                                   ///< ::UR_DEVICE_AFFINITY_DOMAIN_FLAG_L2_CACHE,
-                                                                   ///< ::UR_DEVICE_AFFINITY_DOMAIN_FLAG_L1_CACHE,
+                                                                   ///< ::UR_DEVICE_AFFINITY_DOMAIN_FLAG_L2_CACHE, ::UR_DEVICE_AFFINITY_DOMAIN_FLAG_L1_CACHE,
                                                                    ///< and partition the device into sub devices comprised of compute units
                                                                    ///< that share memory subsystems at this level.
     /// @cond
@@ -2610,8 +2607,7 @@ typedef struct ur_image_desc_t {
 ///
 /// @details
 ///     - The primary ::ur_image_format_t that must be supported by all the
-///       adapters are {UR_IMAGE_CHANNEL_ORDER_RGBA,
-///       UR_IMAGE_CHANNEL_TYPE_UNORM_INT8},
+///       adapters are {UR_IMAGE_CHANNEL_ORDER_RGBA, UR_IMAGE_CHANNEL_TYPE_UNORM_INT8},
 ///       {UR_IMAGE_CHANNEL_ORDER_RGBA, UR_IMAGE_CHANNEL_TYPE_UNORM_INT16},
 ///       {UR_IMAGE_CHANNEL_ORDER_RGBA, UR_IMAGE_CHANNEL_TYPE_SNORM_INT8},
 ///       {UR_IMAGE_CHANNEL_ORDER_RGBA, UR_IMAGE_CHANNEL_TYPE_SNORM_INT16},
@@ -6141,13 +6137,11 @@ urEnqueueKernelLaunch(
     const size_t *pLocalWorkSize,             ///< [in][optional] pointer to an array of workDim unsigned values that
                                               ///< specify the number of local work-items forming a work-group that will
                                               ///< execute the kernel function.
-                                              ///< If nullptr, the runtime implementation will choose the work-group
-                                              ///< size.
+                                              ///< If nullptr, the runtime implementation will choose the work-group size.
     uint32_t numEventsInWaitList,             ///< [in] size of the event wait list
     const ur_event_handle_t *phEventWaitList, ///< [in][optional][range(0, numEventsInWaitList)] pointer to a list of
                                               ///< events that must be complete before the kernel execution.
-                                              ///< If nullptr, the numEventsInWaitList must be 0, indicating that no wait
-                                              ///< event.
+                                              ///< If nullptr, the numEventsInWaitList must be 0, indicating that no wait event.
     ur_event_handle_t *phEvent                ///< [out][optional] return an event object that identifies this particular
                                               ///< kernel execution instance.
 );
@@ -7150,8 +7144,7 @@ urEnqueueUSMFill2D(
     uint32_t numEventsInWaitList,             ///< [in] size of the event wait list
     const ur_event_handle_t *phEventWaitList, ///< [in][optional][range(0, numEventsInWaitList)] pointer to a list of
                                               ///< events that must be complete before the kernel execution.
-                                              ///< If nullptr, the numEventsInWaitList must be 0, indicating that no wait
-                                              ///< event.
+                                              ///< If nullptr, the numEventsInWaitList must be 0, indicating that no wait event.
     ur_event_handle_t *phEvent                ///< [out][optional] return an event object that identifies this particular
                                               ///< kernel execution instance.
 );
@@ -7201,8 +7194,7 @@ urEnqueueUSMMemcpy2D(
     uint32_t numEventsInWaitList,             ///< [in] size of the event wait list
     const ur_event_handle_t *phEventWaitList, ///< [in][optional][range(0, numEventsInWaitList)] pointer to a list of
                                               ///< events that must be complete before the kernel execution.
-                                              ///< If nullptr, the numEventsInWaitList must be 0, indicating that no wait
-                                              ///< event.
+                                              ///< If nullptr, the numEventsInWaitList must be 0, indicating that no wait event.
     ur_event_handle_t *phEvent                ///< [out][optional] return an event object that identifies this particular
                                               ///< kernel execution instance.
 );
@@ -7240,8 +7232,7 @@ urEnqueueDeviceGlobalVariableWrite(
     uint32_t numEventsInWaitList,             ///< [in] size of the event wait list.
     const ur_event_handle_t *phEventWaitList, ///< [in][optional][range(0, numEventsInWaitList)] pointer to a list of
                                               ///< events that must be complete before the kernel execution.
-                                              ///< If nullptr, the numEventsInWaitList must be 0, indicating that no wait
-                                              ///< event.
+                                              ///< If nullptr, the numEventsInWaitList must be 0, indicating that no wait event.
     ur_event_handle_t *phEvent                ///< [out][optional] return an event object that identifies this particular
                                               ///< kernel execution instance.
 );
@@ -7279,8 +7270,7 @@ urEnqueueDeviceGlobalVariableRead(
     uint32_t numEventsInWaitList,             ///< [in] size of the event wait list.
     const ur_event_handle_t *phEventWaitList, ///< [in][optional][range(0, numEventsInWaitList)] pointer to a list of
                                               ///< events that must be complete before the kernel execution.
-                                              ///< If nullptr, the numEventsInWaitList must be 0, indicating that no wait
-                                              ///< event.
+                                              ///< If nullptr, the numEventsInWaitList must be 0, indicating that no wait event.
     ur_event_handle_t *phEvent                ///< [out][optional] return an event object that identifies this particular
                                               ///< kernel execution instance.
 );
@@ -7320,8 +7310,7 @@ urEnqueueReadHostPipe(
     const ur_event_handle_t *phEventWaitList, ///< [in][optional][range(0, numEventsInWaitList)] pointer to a list of
                                               ///< events that must be complete before the host pipe read.
                                               ///< If nullptr, the numEventsInWaitList must be 0, indicating that no wait event.
-    ur_event_handle_t *phEvent                ///< [out][optional] returns an event object that identifies this read
-                                              ///< command
+    ur_event_handle_t *phEvent                ///< [out][optional] returns an event object that identifies this read command
                                               ///< and can be used to query or queue a wait for this command to complete.
 );
 
@@ -9117,13 +9106,11 @@ urEnqueueCooperativeKernelLaunchExp(
     const size_t *pLocalWorkSize,             ///< [in][optional] pointer to an array of workDim unsigned values that
                                               ///< specify the number of local work-items forming a work-group that will
                                               ///< execute the kernel function.
-                                              ///< If nullptr, the runtime implementation will choose the work-group
-                                              ///< size.
+                                              ///< If nullptr, the runtime implementation will choose the work-group size.
     uint32_t numEventsInWaitList,             ///< [in] size of the event wait list
     const ur_event_handle_t *phEventWaitList, ///< [in][optional][range(0, numEventsInWaitList)] pointer to a list of
                                               ///< events that must be complete before the kernel execution.
-                                              ///< If nullptr, the numEventsInWaitList must be 0, indicating that no wait
-                                              ///< event.
+                                              ///< If nullptr, the numEventsInWaitList must be 0, indicating that no wait event.
     ur_event_handle_t *phEvent                ///< [out][optional] return an event object that identifies this particular
                                               ///< kernel execution instance.
 );
@@ -9182,8 +9169,7 @@ urEnqueueTimestampRecordingExp(
     uint32_t numEventsInWaitList,             ///< [in] size of the event wait list
     const ur_event_handle_t *phEventWaitList, ///< [in][optional][range(0, numEventsInWaitList)] pointer to a list of
                                               ///< events that must be complete before the kernel execution.
-                                              ///< If nullptr, the numEventsInWaitList must be 0, indicating no wait
-                                              ///< events.
+                                              ///< If nullptr, the numEventsInWaitList must be 0, indicating no wait events.
     ur_event_handle_t *phEvent                ///< [in,out] return an event object that identifies this particular kernel
                                               ///< execution instance. Profiling information can be queried
                                               ///< from this event as if `hQueue` had profiling enabled. Querying

scripts/core/adapter.yml

@@ -28,7 +28,7 @@ params:
     - type: "uint32_t"
       name: NumEntries
       desc: |
-            [in] the number of adapters to be added to phAdapters. 
+            [in] the number of adapters to be added to phAdapters.
             If phAdapters is not NULL, then NumEntries should be greater than zero, otherwise $X_RESULT_ERROR_INVALID_SIZE,
             will be returned.
     - type: "$x_adapter_handle_t*"
@@ -39,7 +39,7 @@ params:
     - type: "uint32_t*"
       name: "pNumAdapters"
       desc: |
-            [out][optional] returns the total number of adapters available. 
+            [out][optional] returns the total number of adapters available.
 returns:
     - $X_RESULT_ERROR_INVALID_SIZE:
         - "`NumEntries == 0 && phAdapters != NULL`"

scripts/core/context.yml

@@ -95,7 +95,7 @@ etors:
     - name: REFERENCE_COUNT
       desc: |
             [uint32_t] Reference count of the context object.
-            The reference count returned should be considered immediately stale. 
+            The reference count returned should be considered immediately stale.
             It is unsuitable for general use in applications. This feature is provided for identifying memory leaks.
     - name: USM_MEMCPY2D_SUPPORT
       desc: "[$x_bool_t] to indicate if the $xEnqueueUSMMemcpy2D entrypoint is supported."
@@ -107,11 +107,11 @@ etors:
       desc: "[$x_memory_scope_capability_flags_t] return a bit-field of atomic memory scope capabilities."
     - name: ATOMIC_FENCE_ORDER_CAPABILITIES
       desc: |
-            [$x_memory_order_capability_flags_t] return a bit-field of atomic memory fence order capabilities. 
+            [$x_memory_order_capability_flags_t] return a bit-field of atomic memory fence order capabilities.
             Zero is returned if the backend does not support context-level fences.
     - name: ATOMIC_FENCE_SCOPE_CAPABILITIES
       desc: |
-            [$x_memory_scope_capability_flags_t] return a bit-field of atomic memory fence scope capabilities. 
+            [$x_memory_scope_capability_flags_t] return a bit-field of atomic memory fence scope capabilities.
             Zero is returned if the backend does not support context-level fences.
 --- #--------------------------------------------------------------------------
 type: function
@@ -122,7 +122,7 @@ decl: static
 ordinal: "0"
 analogue:
     - "**clReleaseContext**"
-details:    
+details:
     - "The application may call this function from simultaneous threads for the same context."
     - "The implementation of this function should be thread-safe."
 params:
@@ -157,7 +157,7 @@ params:
       name: pPropValue
       desc: |
             [out][optional][typename(propName, propSize)] array of bytes holding the info.
-            if propSize is not equal to or greater than the real number of bytes needed to return 
+            if propSize is not equal to or greater than the real number of bytes needed to return
             the info then the $X_RESULT_ERROR_INVALID_SIZE error is returned and pPropValue is not used.
     - type: "size_t*"
       name: pPropSizeRet

scripts/core/device.yml

@@ -15,8 +15,8 @@ ordinal: "2"
 --- #--------------------------------------------------------------------------
 type: macro
 desc: |
-      Target identification strings for $x_device_binary_t.pDeviceTargetSpec 
-      A device type represented by a particular target triple requires specific 
+      Target identification strings for $x_device_binary_t.pDeviceTargetSpec
+      A device type represented by a particular target triple requires specific
       binary images. We need to map the image type onto the device target triple
 name: "$X_DEVICE_BINARY_TARGET_UNKNOWN"
 value: "\"<unknown>\""
@@ -35,7 +35,7 @@ value: "\"spir64\""
 --- #--------------------------------------------------------------------------
 type: macro
 desc: |
-      Device-specific binary images produced from SPIR-V 64-bit <-> various 
+      Device-specific binary images produced from SPIR-V 64-bit <-> various
       "spir64_*" triples for specific 64-bit OpenCL CPU devices
 name: "$X_DEVICE_BINARY_TARGET_SPIRV64_X86_64"
 value: "\"spir64_x86_64\""
@@ -75,7 +75,7 @@ members:
       name: pDeviceTargetSpec
       desc: |
             [in] null-terminated string representation of the device's target architecture.
-            For example: 
+            For example:
             + $X_DEVICE_BINARY_TARGET_UNKNOWN
             + $X_DEVICE_BINARY_TARGET_SPIRV32
             + $X_DEVICE_BINARY_TARGET_SPIRV64
@@ -326,7 +326,7 @@ etors:
     - name: REFERENCE_COUNT
       desc: |
             [uint32_t] Reference count of the device object.
-            The reference count returned should be considered immediately stale. 
+            The reference count returned should be considered immediately stale.
             It is unsuitable for general use in applications. This feature is provided for identifying memory leaks.
     - name: IL_VERSION
       desc: "[char[]] IL version"
@@ -356,7 +356,7 @@ etors:
       desc: "[uint32_t] maximum number of sub-devices when the device is partitioned"
     - name: PARTITION_AFFINITY_DOMAIN
       desc: |
-            [$x_device_affinity_domain_flags_t] Returns a bit-field of the supported affinity domains for partitioning. 
+            [$x_device_affinity_domain_flags_t] Returns a bit-field of the supported affinity domains for partitioning.
             If the device does not support any affinity domains, then 0 will be returned.
     - name: PARTITION_TYPE
       desc: "[$x_device_partition_property_t[]] return an array of $x_device_partition_property_t for properties specified in $xDevicePartition"
@@ -412,7 +412,7 @@ etors:
       desc: "[$x_bool_t] support for bfloat16"
     - name: MAX_COMPUTE_QUEUE_INDICES
       desc: |
-            [uint32_t] Returns 1 if the device doesn't have a notion of a 
+            [uint32_t] Returns 1 if the device doesn't have a notion of a
             queue index. Otherwise, returns the number of queue indices that are
             available for this device.
     - name: KERNEL_SET_SPECIALIZATION_CONSTANTS
@@ -548,10 +548,10 @@ etors:
       value: "$X_BIT(4)"
     - name: NEXT_PARTITIONABLE
       desc: |
-            Split the device along the next partitionable affinity domain. 
+            Split the device along the next partitionable affinity domain.
             The implementation shall find the first level along which the device
-            or sub device may be further subdivided in the order: 
-            $X_DEVICE_AFFINITY_DOMAIN_FLAG_NUMA, $X_DEVICE_AFFINITY_DOMAIN_FLAG_L4_CACHE, $X_DEVICE_AFFINITY_DOMAIN_FLAG_L3_CACHE, $X_DEVICE_AFFINITY_DOMAIN_FLAG_L2_CACHE, $X_DEVICE_AFFINITY_DOMAIN_FLAG_L1_CACHE, 
+            or sub device may be further subdivided in the order:
+            $X_DEVICE_AFFINITY_DOMAIN_FLAG_NUMA, $X_DEVICE_AFFINITY_DOMAIN_FLAG_L4_CACHE, $X_DEVICE_AFFINITY_DOMAIN_FLAG_L3_CACHE, $X_DEVICE_AFFINITY_DOMAIN_FLAG_L2_CACHE, $X_DEVICE_AFFINITY_DOMAIN_FLAG_L1_CACHE,
             and partition the device into sub devices comprised of compute units that share memory subsystems at this level.
       value: "$X_BIT(5)"
 --- #--------------------------------------------------------------------------
@@ -679,7 +679,7 @@ params:
     - type: "uint32_t"
       name: NumBinaries
       desc: |
-            [in] the number of binaries passed in ppBinaries. 
+            [in] the number of binaries passed in ppBinaries.
             Must greater than or equal to zero otherwise $X_RESULT_ERROR_INVALID_VALUE is returned.
     - type: "uint32_t*"
       name: pSelectedBinary
@@ -850,13 +850,13 @@ params:
       desc:  "[in] handle of the device instance"
     - type: "uint64_t*"
       name: pDeviceTimestamp
-      desc: | 
-            [out][optional] pointer to the Device's global timestamp that 
+      desc: |
+            [out][optional] pointer to the Device's global timestamp that
             correlates with the Host's global timestamp value
     - type: "uint64_t*"
       name: pHostTimestamp
       desc: |
-            [out][optional] pointer to the Host's global timestamp that 
+            [out][optional] pointer to the Host's global timestamp that
             correlates with the Device's global timestamp value
 --- #--------------------------------------------------------------------------
 type: enum