Skip to content

Commit ee72fe3

Browse files
committed
fix TODO comments
1 parent a853ac1 commit ee72fe3

1 file changed

Lines changed: 16 additions & 16 deletions

File tree

api/opencl_runtime_layer.asciidoc

Lines changed: 16 additions & 16 deletions
Original file line numberDiff line numberDiff line change
@@ -6090,7 +6090,7 @@ Otherwise, it returns one of the following errors:
60906090
** if _event_wait_list_ is `NULL` and _num_events_in_wait_list_ is greater than zero
60916091
** if _event_wait_list_ is not `NULL` and _num_events_in_wait_list_ is zero
60926092
** if event objects in _event_wait_list_ are not valid events
6093-
// TODO: Do we want this to be an error? For other APIs, it is only an error when the API is blocking.
6093+
// TODO: Do we want this to be an error? For other APIs, it is only an error when the API is blocking.
60946094
* {CL_EXEC_STATUS_ERROR_FOR_EVENTS_IN_WAIT_LIST}
60956095
** if the execution status of any of the events in _event_wait_list_ is a negative integer value indicating an error.
60966096
This error code is <<unified-spec, missing before>> version 1.1.
@@ -6188,7 +6188,7 @@ Otherwise, it returns one of the following errors:
61886188
** if _event_wait_list_ is `NULL` and _num_events_in_wait_list_ is greater than zero
61896189
** if _event_wait_list_ is not `NULL` and _num_events_in_wait_list_ is zero
61906190
** if event objects in _event_wait_list_ are not valid events
6191-
// TODO: Do we want this to be an error? For other APIs, it is only an error when the API is blocking.
6191+
// TODO: Do we want this to be an error? For other APIs, it is only an error when the API is blocking.
61926192
* {CL_EXEC_STATUS_ERROR_FOR_EVENTS_IN_WAIT_LIST}
61936193
** if the execution status of any of the events in _event_wait_list_ is a negative integer value indicating an error.
61946194
This error code is <<unified-spec, missing before>> version 1.1.
@@ -8230,7 +8230,7 @@ Otherwise, it returns one of the following errors:
82308230
* {CL_INVALID_VALUE}
82318231
** if _svm_pointers_ is `NULL` and _num_svm_pointers_ is greater than zero
82328232
** if _svm_pointers_ is not `NULL` and _num_svm_pointers_ is zero
8233-
// TODO: error condition for invalid SVM pointers?
8233+
// TODO: error condition for invalid SVM pointers?
82348234
* {CL_INVALID_EVENT_WAIT_LIST}
82358235
** if _event_wait_list_ is `NULL` and _num_events_in_wait_list_ is greater than zero
82368236
** if _event_wait_list_ is not `NULL` and _num_events_in_wait_list_ is zero
@@ -12158,19 +12158,19 @@ Otherwise, it returns one of the following errors:
1215812158
* {CL_INVALID_OPERATION}
1215912159
** if SVM pointers are set as arguments for _kernel_ and the device associated with _command_queue_ does not support SVM
1216012160
** if system pointers are set as arguments for _kernel_ the device associated with _command_queue_ does not support fine-grain system SVM
12161-
// TODO: Do we still need these explicit examples?
12162-
// * {CL_OUT_OF_RESOURCES} if there is a failure to queue the execution
12163-
// instance of _kernel_ on the command-queue because of insufficient
12164-
// resources needed to execute the kernel.
12165-
// For example, the explicitly specified _local_work_size_ causes a failure
12166-
// to execute the kernel because of insufficient resources such as
12167-
// registers or local memory.
12168-
// Another example would be the number of read-only image args used in
12169-
// _kernel_ exceed the {CL_DEVICE_MAX_READ_IMAGE_ARGS} value for device or
12170-
// the number of write-only and read-write image args used in _kernel_
12171-
// exceed the {CL_DEVICE_MAX_READ_WRITE_IMAGE_ARGS} value for device or the
12172-
// number of samplers used in _kernel_ exceed {CL_DEVICE_MAX_SAMPLERS} for
12173-
// device.
12161+
// TODO: Do we still need these explicit examples?
12162+
// * {CL_OUT_OF_RESOURCES} if there is a failure to queue the execution
12163+
// instance of _kernel_ on the command-queue because of insufficient
12164+
// resources needed to execute the kernel.
12165+
// For example, the explicitly specified _local_work_size_ causes a failure
12166+
// to execute the kernel because of insufficient resources such as
12167+
// registers or local memory.
12168+
// Another example would be the number of read-only image args used in
12169+
// _kernel_ exceed the {CL_DEVICE_MAX_READ_IMAGE_ARGS} value for device or
12170+
// the number of write-only and read-write image args used in _kernel_
12171+
// exceed the {CL_DEVICE_MAX_READ_WRITE_IMAGE_ARGS} value for device or the
12172+
// number of samplers used in _kernel_ exceed {CL_DEVICE_MAX_SAMPLERS} for
12173+
// device.
1217412174
* {CL_OUT_OF_RESOURCES}
1217512175
** if there is a failure to allocate resources required by the OpenCL
1217612176
implementation on the device

0 commit comments

Comments
 (0)