OpenCL Compiler supports multi-core ARM-based SoCs.
August 24, 2012 -
In addition to basic debugging support, PGCL(TM) 12.7 provides automatic vectorization for ARM NEON(TM) general-purpose Single-Instruction Multiple Data engine. Program automatically generates NEON instructions for vectorizable loops contained in OpenCL kernel functions and which operate on these data types. Compiler recognizes optimization options including fast, Msafeptr, and Minfo, and provides support for compiler pragmas for local control of optimizations within OpenCL source files.
|Original Press release |
10 Maguire Road
Lexington, MA, 02421
The Portland Group Updates Its OpenCL Compiler for Multi-Core ARM
Latest PGCL includes automatic generation of NEON/SIMD instructions
Portland, Oregon, -The Portland Group® (PGI), a wholly-owned subsidiary of STMicroelectronics and the leading independent supplier of compilers and tools for high-performance computing, today announced the release of PGCL 12.7. PGCL(TM) is the PGI OpenCL framework for multi-core ARM-based Systems-on-Chips (SoCs), currently available on ST-Ericsson NovaThor(TM) platforms. PGCL includes a PGI OpenCL compiler for multi-core ARM CPUs as a compute device and complements OpenCL for GPUs.
"This significant update to the PGI OpenCL compiler includes support for several new performance-oriented technologies along with basic debugging support, and reflects our continuing commitment to bring PGI compiler technologies developed in the high-performance computing (HPC) market to the ARM platform," said Douglas Miles, director, The Portland Group.
New PGCL 12.7 Features
· Automatic vectorization for the ARM NEON(TM) general-purpose Single-Instruction Multiple Data (SIMD) engine. NEON technology is a 128-bit SIMD architecture extension for ARM Cortex(TM)-A series CPUs designed to provide acceleration for multimedia and other data-processing intensive applications. NEON instructions perform packed SIMD processing on signed or unsigned 8-bit, 16-bit, 32-bit and 64-bit integer, or single-precision floating-point data types. PGCL now automatically generates NEON instructions for vectorizable loops contained in OpenCL kernel functions and which operate on these data types.
· Native dynamic OpenCL kernel compilation is now the default on Android ARM devices, enabling deployment of dynamically-compiled OpenCL kernels in production applications for mobile devices. The PGCL OpenCL dynamic compiler now recognizes optimization options including fast (PGI's default performance optimization option), Msafeptr (enables optimization in the presence of pointers) and Minfo (for displaying compiler optimization feedback to application developers).
· Support for compiler "pragmas" for local control of optimizations within OpenCL source files. Optimizations that can be controlled on a loop or function basis include NEON/SIMD vectorization, loop unrolling, dependence checking, safe pointer declarations and other optimization options. Pragmas are programming language constructs added to source code by programmers to instruct a compiler to process the delineated code blocks in some special manner while maintaining full source code portability to other compilers and platforms.
· Support for debugging of OpenCL host code and statically-compiled OpenCL kernels on Android/ARM devices using the gdb debugger or print statements.
PGCL is an OpenCL framework for compiling and running OpenCL 1.1 embedded profile applications on the ST-Ericsson NovaThor(TM) U8500 and follow-on platforms using a single ARM core as the OpenCL host and multiple ARM cores as an OpenCL compute device. The PGI OpenCL framework runs on Linux/x86 compilation host platforms and is integrated with the Android NDK toolchain to generate binary executables for ST-Ericsson NovaThor platforms running the Android operating system.
About NovaThor Platforms
ST-Ericsson's NovaThor platforms fully integrate application engines, modems and connectivity chipsets that allow device manufacturers to quickly roll out advanced smartphones and tablets with advanced multimedia capabilities. The NovaThor platform is the first integrated smartphone platform to offer the latest SMP (Symmetric Multi-Processing) dual core technology in a high-performance, low power and cost-optimized package, enabling an immersive multimedia experience for next-generation smartphones. Both cores are identical and can be used independently or combined as one processing engine.
More information on the NovaThor platforms is available from ST-Ericsson at http://www.stericsson.com/products/smartphone-platforms.jsp
OpenCL is a programming model for heterogenous computing systems comprised of CPUs, GPUs and other computing devices, and has been standardized by Khronos and adopted by a number of CPU and GPU manufacturers including Intel, AMD/ATI, NVIDIA and Imagination Technologies. PGCL is the first OpenCL compiler for Android targeting multi-core ARM processors as an OpenCL compute device. ARM processors power the vast majority of mobile and embedded computing platforms.
PGCL conforms to the OpenCL specification. OpenCL and the OpenCL logo are trademarks of Apple Inc. used with permission by Khronos.
Price and Availability
PGI OpenCL targeting ST-Ericsson NovaThor platforms including code examples and sample Dalvik applications is freely available by registering on The Portland Group website at www.pgroup.com/pgcl.
About The Portland Group
The Portland Group, a wholly-owned subsidiary of STMicroelectronics, is the premier supplier of high-performance parallel Fortran, C, and C++ compilers and tools for workstations, servers, and clusters based on x64 processors from Intel and AMD, and GPUs accelerators from NVIDIA. PGI also develops products for ST and ST-Ericsson embedded processors. Further information on The Portland Group products can be found at www.pgroup.com, by calling Sales at (503) 682-2806, or by email to firstname.lastname@example.org.
+1 (781) 591-0354