Codeplay
Private | |
Industry | Technology |
Founded | 2002 |
Founder | Andrew Richards |
Headquarters | Edinburgh, Lothian, UK |
Key people |
Andrew Richards (CEO) Jens-Uwe Dolinsky (CTO) |
Products |
Compilers Debuggers Runtimes Testing tools |
Services |
Compiler development Debugger development Runtime development |
Number of employees | 40 (2015) |
Website |
www |
Codeplay Software Limited is a privately owned software tools developer based in Edinburgh, Scotland. Codeplay produces compilers, debuggers, runtimes, testing systems, and other specialized tools to aid software development for heterogeneous systems and special purpose processor architectures, including GPUs and DSPs. Codeplay is a contributing member of the Multicore Association, the Khronos Group,[1] and the HSA Foundation.[2]
History
Codeplay was founded in 2002 by Andrew Richards, an experienced games developer, and formerly head of Software Development at Eutechnyx. Initial funding for the company was provided by Jez San OBE, founder of Argonaut Games and ARC International, who remains the majority shareholder. Codeplay began its business developing compilers aimed at games programmers, releasing its VectorC compiler for PlayStation 2 and x86 Windows PC. In 2005, Codeplay shifted focus to developing bespoke C/C++ compilers for processor designers, and has since expanded its services to include development of debuggers, runtimes, and testing tools.
In 2011, Codeplay announced that it had provided the real-time car damage system for NASCAR The Game: 2011, utilising its Offload technology[3]
In 2013, Codeplay formed an R&D division,[4] and received Investors in People accreditation.[5]
In 2014, Codeplay announced that it was working on an implementation of the Khronos Group's new provisional standard for heterogeneous computing, SYCL. Codeplay's CEO, Andrew Richards, currently chairs the working group for this standard within the Khronos Group.
Products
Sieve C++ Multicore Programming System
The Sieve C++ Multicore Programming System is a toolset that allows programmers to quickly and easily adapt existing C and C++ software, or write new software, to take advantage of new multi-core processor architectures.
VectorC
VectorC is a Retargetable C/C++ compiler engine used to create C and C++ compilers for custom-built processor architectures.[6] Codeplay describes VectorC as being optimized for SIMD processors, DSPs, vector units and multi core processors.
VectorC, as its name suggests, was designed from the outset to exploit vectorization. It can automatically take advantage of advanced CPU 'vector' units via SIMD instruction such as MMX, SSE/SSE2, 3D Now and Altivec. VectorC is based around a common optimization core so that all appropriate existing optimizations can be used on the new target architecture it is being customized for. The Optimizer can query the back-end to see what optimizations are possible or suitable on the target.
VectorC also supports C++ to C compilation through an ANSI C compliant back-end. This enables the compilation of C++ code, with or without additional language extensions, to any architecture where a C compiler already exists. This feature is used in Codeplay's Sieve C++ Parallel Programming System to generate parallelized code that can be ported to any multicore architecture with a native C compiler.
Codeplay state that VectorC performs all the standard non-vector optimizations expected from high-performance compilers.
The VectorC engine has been designed to cope with multiple memory spaces, distributed latencies and an optimize data-movement using double-buffered streaming DMA when required, in addition to standard write combining and prefetching functions. There is support for Software pipelining, automatically parallelizing loops on pipelined architectures.
VectorC has extensive support for portable intrinsic functions, letting users write complex vector operations as built in functions. These are converted into the best combination of instructions on each architecture that the source code is compiled for.
Codeplay continues to offer VectorC-based custom compilers to clients. VectorC is also described by Codeplay as being the basis of Sieve C++ Multicore Programming System.
Research
Codeplay has contributed to the following EU-funded research projects:
- CARP: Correct and Efficient Accelerator Programming[7]
- LPGPU: Low-power GPU[8][9]
- PEPPHER: Performance Portability and Programmability for Heterogeneous Many-core Architectures[10]
References
- ↑ "Khronos Contributing Members". Retrieved 10 April 2014.
- ↑ "HSA Foundation Members". Retrieved 10 April 2014
- ↑ "Codeplay Teams With Eutechnyx For Whole New World Of Damage". Scottish Games Network. 27 April 2011. Retrieved 3 April 2014.
- ↑ "Codeplay Software Form New R&D Division". Scottish Games Network. 26 June 2013. Retrieved 3 April 2014.
- ↑ "February 2013 -- Investors in People Scotland" Archived 2014-04-03 at Archive.is. Retrieved 3 April 2014.
- ↑ "VectorC Retargetable Compiler Platform". Retrieved 3 April 2014.
- ↑ "CARP: Correct and Efficient Accelerator Programming". Retrieved 3 April 2014
- ↑ "Consortium | LPGPU.org". Retrieved 3 April 2014
- ↑ "European Consortium Awarded 2.8M€ Grant For Research Into Low Energy Graphics Processing". 9 November 2011. Retrieved 3 April 2014.
- ↑ "PEPPHER Partners". Retrieved 3 April 2014