Unified, Cross-Architecture Programming Model: Product Brief
Unified, Cross-Architecture Programming Model: Product Brief
Unified, Cross-Architecture
Programming Model
Highlights
Data Parallel C++ Language for Direct Programming
Data Parallel C++ (DPC++) is an evolution of C++ that incorporates SYCL*.
It allows code reuse across hardware targets and enables high productivity
and performance across CPU, GPU, and FPGA architectures, while permitting
accelerator-specific tuning.
• Allows code reuse across hardware targets—CPUs, • Intel® VTune™ Profiler(Beta): Find and optimize performance
GPUs, and FPGAs bottlenecks across CPU, GPU, and FPGA systems.
• Permits custom tuning for individual accelerators • Intel® Advisor (Beta): Design code for efficient
vectorization, threading, and offloading to accelerators.
• Domain-specific libraries and the Intel® Distribution
for Python* to provide drop-in acceleration across • Intel® oneAPI Video Processing Library(Beta): Deliver
relevant architectures fast, high-quality, real-time video decoding, encoding,
transcoding, and processing for broadcasting, live
• Enhanced profiling, design assistance, and debug tools streaming and VOD, cloud gaming, and more.
to complete the kit’
• Intel® oneAPI Deep Neural Network Library (Beta):
Here’s what you get: Develop fast neural network frameworks on Intel CPUs
and GPUs with performance-optimized building blocks.
• Intel® oneAPI DPC++ Compiler (Beta): Targets CPUs and
accelerators using a single codebase while permitting • Intel® oneAPI Collective Communications Library(Beta):
custom tuning. Implement optimized communication patterns in deep
learning frameworks. Use the components separately or
• Intel® DPC++ Compatibility Tool (Beta): Migrate CUDA* together as the foundation of deep learning frameworks.
source code to DPC++ code with this assistant.
• Intel® Integrated Performance Primitives: Speed
• Intel® oneAPI DPC++ Library(Beta): Speed up data parallel performance of imaging, signal processing, data
workloads with these key productivity algorithms and compression, and more.
functions.
• GDB*: Enables deep, system-wide debug of DPC++, C,
• Intel® oneAPI Threading Building Blocks(Beta): Simplify C++, and Fortran code.
parallelism with this advanced threading and memory-
management template library. • Intel® FPGA Add-On for oneAPI Base Toolkit(Beta)
(Optional): Program these reconfigurable hardware
accelerators to speed specialized, data-centric workloads.
2
Add Domain-Specific Toolkits for Your accelerators through this toolkit powered by oneAPI
Specialized Workloads components.
Besides the Intel oneAPI Base Toolkit that serves a broad • Intel® AI Analytics Toolkit(Beta): Achieve end-to-end
set of developers’ needs, there are four add-on toolkits that performance for AI workloads with this toolkit powered
combine it to give you the specialized tools you need: by oneAPI. Accelerate each step in the pipeline—training
deep neural networks, integrating trained models into
• Intel® oneAPI HPC Toolkit(Beta): Deliver fast applications applications for inference, and executing functions for
that scale with tools to build, analyze, optimize, and data science and analytics.
scale HPC applications with the latest techniques in
vectorization, multithreading, multi-node parallelization, • Intel® System Bring-Up Toolkit(Beta): Strengthen system
and memory optimization. reliability and optimize system power and performance
with this collection of debug, trace, and power and
• Intel® oneAPI IoT Toolkit(Beta): Accelerate development of performance analysis tools to let you quickly debug and
smart, connected devices for healthcare, smart homes, analyze the entire platform.
aerospace, security, and more.
• Intel® oneAPI Rendering Toolkit(Beta): Get powerful
Try Your Code in the Intel® DevCloud
rendering and ray-tracing libraries for high-fidelity
Develop, run, and optimize your Intel oneAPI code in the
visualization applications—for medical research,
Intel® DevCloud—a free development sandbox with access to
geophysical exploration, movie-making, and more—
the latest Intel CPU, GPU, and FPGA hardware and Intel
that require massive amounts of raw data to be quickly
oneAPI software.
rendered into rich, realistic visuals.
• Intel® oneAPI DL Framework Developer Toolkit(Beta): Get Started
Develop new—or customize existing—deep learning
frameworks using common APIs. Optimize for high- • Learn More about Intel oneAPI Products >
performance on Intel CPUs and GPUs for either single-
• Get the Intel oneAPI Base Toolkit >
node or multi-node distributed processing.
There are three more toolkits closely related to oneAPI: • Check out the Intel DevCloud >
Software