Modern GPUs are able to perform significantly more arithmetic operations than transfers of a single word to or from global memory. Hence, many GPU kernels are limited by memory bandwidth and cannot exploit the arithmetic power of GPUs. However, the memory locality can be often improved by kernel fusion when a sequence of kernels is executed and some kernels in this sequence share data. In this paper, we show how kernels performing map, reduce or their nested combinations can be fused automatically by our source-to-source compiler. To demonstrate the usability of the compiler, we have implemented several BLAS-1 and BLAS-2 routines and show how the performance of their sequences can be improved by fusions. Compared to similar sequences using CUBLAS, our compiler is able to generate code that is up to 2.61x faster for the examples tested.
(J. Filipovič, M. Madzin, J. Fousek, L. Matyska: “Optimizing CUDA Code By Kernel Fusion – Application on BLAS”, submitted to Parallel Computing, May 2013. [preprint])
Alea.cuBase allows to create GPU accelerated applications at all levels of sophistication, from simple GPU kernels up to complex GPU algorithms using textures, shared memory and other advanced GPU programming techniques, fully integrated into .NET. The GPU kernels are developed in functional language F# and are callable from any other .NET language. No additional wrappers or assembly translation processes are required. Alea.cuBase allows dynamic creation of GPU code at run time, thereby opening completely new dimensions for GPU accelerated applications. Trial versions are available at http://www.quantalea.net/products.
PGI Release 12.6 is now out. New in this release:
- PGI Accelerator compilers — first release of the Fortran and C compilers to include comprehensive support for the OpenACC 1.0 specification including the acc cache construct and the entire OpenACC API library. See the PGI Accelerator page for a complete list of supported features.
- CUDA Toolkit — PGI Accelerator compilers and CUDA Fortran now include support for CUDA Toolkit version 4.2; version 4.1 is now the default.
Download a free trial from the PGI website at http://www.pgroup.com/support/download_pgi2012.php?view=current. Upcoming PGI webinar with Michael Wolfe. 9:00AM PDT, July 31st sponsored by NVIDIA: “Using OpenACC Directives with the PGI Accelerator Compilers”. Register at http://www.pgroup.com/webinar212.htm?clicksource=gpgpu712.
PORTLAND, Ore., March 5 — The Portland Group, a wholly-owned subsidiary of STMicroelectronics, today announced availability of the 2012 release of the PGI line of high-performance parallelizing compilers and development tools for Linux, OS X and Windows. PGI 2012 is the first general release to include support for the OpenACC directive-based programming model for NVIDIA CUDA-enabled Graphics Processing Units (GPUs). This release is also the first to include the fully feature-enabled PGI CUDA C/C++ compiler for multi-core x64 CPUs from Intel and AMD. In addition, PGI 2012 includes a number of performance and feature enhancements for multi-core x64 processor-based HPC systems.
Chai is a new managed platform for GPGPU. It is a free and open source clean room workalike of the PeakStream platform. While not production-ready, the just-released alpha version is able to compile and run non-trivial PeakStream demo code on AMD and NVIDIA GPUs (e.g. conjugate gradient).
Chai combines an application virtual machine, garbage collection, auto-tuning JIT compiler, and high level array programming language implemented as an embedded domain-specific language in C++. The JIT back-end uses expectation-maximization to auto-tune and generate vectorized OpenCL. The JIT includes auto-tuned model families for GEMM and GEMV. Although originally developed for AMD GPUs, these parameterized kernel families also generalize to NVIDIA GPUs.
Today NVIDIA released CUDA 4.1, including a new CUDA Toolkit, SDK, Visual Profiler, Parallel Nsight IDE and NVIDIA device driver.
CUDA 4.1 makes it easier to accelerate scientific research with GPUs with key features including
- a redesigned Visual Profiler with automated performance analysis and expert guidance;
- a new LLVM-based compiler that generates up to 10% faster code; and
- 1000+ new imaging and signal processing functions in the NPP library.
The CuSparse library included with CUDA 4.1 has a new tridiagonal solver and 2x faster sparse matrix-vector multiplication using the ELL hybrid format, and the CuRand library included with CUDA 4.1 has two new random number generators. Read the rest of this entry »
CLCC, the light-weight and flexible utility for integrating OpenCL source builds into your project has just been updated to version 0.3.0. This version allows developers to save compiled binaries as object files for distribution with their programs and adds a series of options to select specific target platform/device combinations. Documentation and further information is available at http://clcc.sourceforge.net.
A major new release of the Intel SPMD Program Compiler (ispc) was posted on December 5, 2011. ispc is an extended version of the C programming language with support for “single program, multiple data” (SPMD) programming on the CPU; the SPMD model makes it easy to harness the full power of both the SIMD vector units and multiple cores on modern CPUs. The major features added in the 1.1 release include:
- Full support for pointers, including pointer arithmetic, function pointers, and all other features of pointers in C.
- A new parallel “foreach” statement, for more easily mapping computation to data.
- Substantially revised documentation, including a new Performance Guide.
- Many other small bug fixes and improvements.
ispc is open-source and is licensed under the BSD license. Source and binaries are available from http://ispc.github.com.
Microsoft has announced that the next version of Visual Studio will contain technology labeled C++ Accelerated Massive Parallelism (C++ AMP) to enable C++ developers to take advantage of the GPU for computation purposes. More information is available in the MSDN blog posts here and here.
Intel has announced ispc, The Intel SPMD Program Compiler, now available in source and binary form from http://ispc.github.com.
ispc is a new compiler for “single program, multiple data” (SPMD) programs; the same model that is used for (GP)GPU programming, but here targeted to CPUs. ispc compiles a C-based SPMD programming language to run on the SIMD units of CPUs; it frequently provides a a 3x or more speedup on CPUs with 4-wide SSE units, without any of the difficulty of writing intrinsics code. There were a few principles and goals behind the design of ispc:
- To build a small C-like language that would deliver excellent performance to performance-oriented programmers who want to run SPMD programs on the CPU.
- To provide a thin abstraction layer between the programmer and the hardware—in particular, to have an execution and data model where the programmer can cleanly reason about the mapping of their source program to compiled assembly language and the underlying hardware.
- To make it possible to harness the computational power of the SIMD vector units without the extremely low-programmer-productivity activity of directly writing intrinsics.
- To explore opportunities from close coupling between C/C++ application code and SPMD ispc code running on the same processor—to have lightweight function calls between the two languages, to share data directly via pointers without copying or reformatting, and so forth.
ispc is an open source compiler with a BSD license. It uses the LLVM Compiler Infrastructure for back-end code generation and optimization and is hosted on github. It supports Windows, Mac, and Linux, with both x86 and x86-64 targets. It currently supports the SSE2 and SSE4 instruction sets, though support for AVX should be available soon.