OpenCL 2.0

E702089

OpenCL 2.0 is a version of the open standard parallel programming framework that enables heterogeneous computing across CPUs, GPUs, and other processors with features like shared virtual memory and improved kernel execution models.

Try in SPARQL Jump to: Statements Referenced by

Statements (46)

Predicate Object
instanceOf OpenCL version
parallel programming framework specification
allows dynamic parallelism on devices
kernels to enqueue other kernels
backwardCompatibleWith OpenCL 1.2 NERFINISHED
basedOn OpenCL 2.0 specification NERFINISHED
conformsTo Khronos OpenCL standard NERFINISHED
defines C-based kernel language extensions
enables heterogeneous computing
feature C11 atomics
SPIR 2.0 support
coarse-grained shared virtual memory
device-side enqueue
fine-grained shared virtual memory
generic address space
improved kernel execution model
improved memory consistency model
on-device work-queue management
parent and child kernels
pipes
program scope global variables
separate compilation and linking of kernels
shared virtual memory
synchronization enhancements
work-group functions
follows OpenCL 1.2 NERFINISHED
improves host-device interoperability
memory sharing between processors
partOf OpenCL NERFINISHED
standardizedBy Khronos Group NERFINISHED
supports CPU computing
DSP computing
FPGA computing
GPU computing
SVM between host and device
accelerator computing
data parallel programming
task parallel programming
targetDomain embedded compute workloads
graphics compute workloads
high-performance computing
usedFor general-purpose GPU computing
image and video processing
parallel acceleration of applications
scientific computing
signal processing

Referenced by (1)

Full triples — surface form annotated when it differs from this entity's canonical label.