-cl-wfv={always|auto|never}

Control whether or not a program is compiled with whole function vectorization enabled.

always:

Always perform whole function vectorization.

auto:

Only perform whole function vectorization if determined by the OpenCL implementation to be optimal.

never:

Never perform whole function vectorization.

To return whole function vectorization information about a kernel object, call the function:

cl_int clGetKernelWFVInfoCODEPLAY(cl_kernel kernel,
                                  cl_device_id device,
                                  cl_uint work_dim,
                                  const size_t *global_work_size,
                                  const size_t *local_work_size,
                                  cl_kernel_wfv_info_codeplay param_name,
                                  size_t param_value_size,
                                  void *param_value,
                                  size_t *param_value_size_ret);

kernel

Specifies the kernel object being queried.

device

Identifies a specific device in the list of devices associated with kernel. The list of devices is the list of devices in the OpenCL context that is associated with kernel. If the list of devices associated with kernel is a single device, device can be a NULL value.

work_dim

The number of dimensions used to specify the work-items in the work-group. work_dim must be greater than zero and less than or equal to CL_DEVICE_MAX_WORK_ITEM_DIMENSIONS.

global_work_size

Points to an array of work_dim unsigned values that describe the number of global work-items in work_dim dimensions that are intended to execute the kernel function. The total number of global work-items is computed as global_work_size [0] × … × global_work_size [work_dim - 1]. If global_work_size and local_work_size are NULL, global_work_size will not be used by the OpenCL runtime when choosing a work-group size. If global_work_size is NULL and local_work_size is not NULL, global_work_size will not be used to determine if the explicitly specified local_work_size is valid.

local_work_size

Points to an array of work_dim unsigned values that describe the number of work-items that make up a work-group (also referred to as the size of the work-group) that is intended to execute the kernel specified by kernel. If local_work_size is NULL, the OpenCL runtime may choose a work-group size. If non-uniform work-groups are supported and local_work_size is NULL, the OpenCL runtime may choose a uniform or non-uniform work-group size. The total number of work-items in the work-group must be less than or equal to the CL_KERNEL_WORK_GROUP_SIZE value specified in the Kernel Object Device Queries table, and the number of work-items specified in local_work_size [0], …, local_work_size [work_dim - 1] must be less than or equal to the corresponding values specified by CL_DEVICE_MAX_WORK_ITEM_SIZES [0], …, CL_DEVICE_MAX_WORK_ITEM_SIZES [work_dim - 1]. The explicitly specified local_work_size will be used to determine how to break the global work-items specified by global_work_size into appropriate work-group instances.

param_name

Specifies the information to query. The list of supported param_name types and the information returned in param_value by clGetKernelWFVInfoCODEPLAY is described in the Kernel WFV Queries table.

param_value

A pointer to memory where the appropriate result being queried is returned. If param_value is NULL, it is ignored.

param_value_size

Used to specify the size in bytes of memory pointed to by param_value. This size must be ≥ size of return type as described in the Kernel WFV Queries table.

param_value_size_ret

Returns the actual size in bytes of data being queried by param_name. If param_value_size_ret is NULL, it is ignored.

clGetKernelWFVInfoCODEPLAY returns CL_SUCCESS if the function is executed successfully. Otherwise, it returns one of the following errors:

• CL_INVALID_DEVICE if device is not in the list of devices associated with kernel or if device is NULL but there is more than one device associated with kernel.

• CL_INVALID_KERNEL if kernel is not a valid kernel object.

• CL_INVALID_VALUE if param_name is not valid, or if size in bytes specified by param_value_size is < size of return type as described in the Kernel WFV Queries table and param_value is not NULL.

• CL_INVALID_WORK_DIMENSION if work_dim is not a valid value (i.e. a value between 1 and CL_DEVICE_MAX_WORK_ITEM_DIMENSIONS).

• CL_INVALID_GLOBAL_WORK_SIZE if any of the values specified in global_work_size [0], …, global_work_size [work_dim - 1] exceed the maximum value representable by size_t on the device on which the kernel-instance is intended to be enqueued.

• CL_INVALID_GLOBAL_WORK_SIZE if any of the values specified in global_work_size [0], …, global_work_size [work_dim - 1] are equal to zero when the OpenCL version is less than 2.1.

• CL_INVALID_WORK_GROUP_SIZE if local_work_size is specified and does not match the required work-group size for kernel in the program source.

• CL_INVALID_WORK_GROUP_SIZE if local_work_size is specified and is not consistent with the required number of sub-groups for kernel in the program source.

• CL_INVALID_WORK_GROUP_SIZE if local_work_size is specified and the total number of work-items in the work-group computed as local_work_size [0] × … local_work_size [work_dim - 1] is greater than the value specified by CL_KERNEL_WORK_GROUP_SIZE in the Kernel Object Device Queries table.

• CL_INVALID_WORK_GROUP_SIZE if the work-group size must be uniform and the local_work_size is not NULL, or is not equal to the required work-group size specified in the kernel source.

• CL_INVALID_WORK_GROUP_SIZE if the number of work-items specified in any of local_work_size [0], … local_work_size [work_dim - 1] is equal to zero.

• CL_INVALID_WORK_ITEM_SIZE if the number of work-items specified in any of local_work_size [0], …, local_work_size [work_dim - 1] is greater than the corresponding values specified by CL_DEVICE_MAX_WORK_ITEM_SIZES [0], …, CL_DEVICE_MAX_WORK_ITEM_SIZES [work_dim - 1].

• CL_OUT_OF_RESOURCES if there is a failure to allocate resources required by the OpenCL implementation on the device.

• CL_OUT_OF_HOST_MEMORY if there is a failure to allocate resources required by the OpenCL implementation on the host.

Add a new Table 3X, clGetKernelWFVInfoCODEPLAY parameter queries: