A new version of the GPU-profiler for CUDA software stack is available at www.lab4241.com. The GPU-profiler is able to deliver per C++ source-code ‘inside’ kernel performance information in a simple, intuitive way, similar to known CPU domain profilers, like Quantify or Valgrind. The new version, GPUPROF version 0.3 (beta), includes improved stability, refined memory tracing, temporal memory analysis, and CUDA API-driver call tracing.
A free, pre-alpha release of Lab4241’s GPGPU profiler is now available at www.lab4241.com. It provides source-code-line performance profiling for C or C++ code and CUDA kernels in a non-intrusive way. The profiler enables the developer to a seamless evaluation of used GPU resources (execution counts, memory access, branch diversions, etc.) per source-line, along with result evaluation in a simple, intuitive GUI, similar as with known CPU profilers like Quantify or valgrind.
AMD CodeXL is a new unified developer tool suite that enables developers to harness the benefits of CPUs, GPUs and APUs. It includes powerful GPU debugging, comprehensive GPU and CPU profiling, and static OpenCL™ kernel analysis capabilities, enhancing accessibility for software developers to enter the era of heterogeneous computing. AMD CodeXL is available for free, both as a Visual Studio® extension and a standalone user interface application for Windows® and Linux®.
AMD CodeXL increases developer productivity by helping them identify programming errors and performance issues in their application quickly and easily. Now developers can debug, profile and analyze their applications with a full system-wide view on AMD APU, GPU and CPUs.
AMD CodeXL user group (requires registration) allows users to interact with the CodeXL team, provide feedback, get support and participate in the beta surveys.
Traditional CPU-based computing environments offer a variety of binary instrumentation frameworks. Instrumentation and analysis tools for GPU environments to date have been more limited. Panoptes is a binary instrumentation framework for CUDA that targets the GPU. By exploiting the GPU to run modified kernels, computationally-intensive programs can be run at the native parallelism of the device during analysis. To demonstrate its instrumentation capabilities, we currently implement a memory addressability and validity checker that targets CUDA programs.
Panoptes traces targeted programs by library interposition at runtime. Read the rest of this entry »
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 »
NVIDIA today announced the release of NVIDIA Parallel Nsight software, the industry’s first development environment for GPU-accelerated applications that work with Microsoft Visual Studio. “By adding functionality specifically for GPU Computing developers, Parallel Nsight makes the power of the GPU more accessible than ever before,” said Sanford Russell, GM of GPU Computing at NVIDIA. NVIDIA Parallel NSight features a CUDA C/C++ debugger and application performance analyzer, and a graphics debugger and inspector. NVIDIA Parallel Nsight supports Windows HPC Server 2008, Windows 7 and Windows Vista. Download Parallel Nsight here.
Advanced Micro Devices (AMD) recently released ATI Stream Profiler version 1.3. ATI Stream Profiler is a Microsoft® Visual Studio® integrated runtime profiler that gathers performance data from the GPU as your OpenCL™ application runs. This information can then be used by developers to discover where the bottlenecks are in their OpenCL™ application and find ways to optimize their application’s performance.
Features of the tool include:
- Measure the execution time of an OpenCL kernel
- Query the hardware performance counters on ATI Radeon graphics cards
- Display the memory traffic from and to GPU
- Compare multiple runs (sessions) of the same or different programs
- Store the profile data for each run in a csv file
- Display the IL and ISA (hardware disassembly) code of the OpenCL kernel
Heterogeneous systems, systems with multiple processors tailored for specialized tasks, are challenging programming environments. While it may be possible for domain experts to optimize a high performance application for a very specific and well documented system, it may not perform as well or even function on a different system. Developers who have less experience with either the application domain or the system architecture may devote a significant effort to writing a program that merely functions correctly. We believe that a comprehensive analysis and modeling framework is necessary to ease application development and automate program optimization on heterogeneous platforms.
This paper reports on an empirical evaluation of 25 CUDA applications on four GPUs and three CPUs, leveraging the Ocelot dynamic compiler infrastructure which can execute and instrument the same CUDA applications on either target. Using a combination of instrumentation and statistical analysis, we record 37 different metrics for each application and use them to derive relationships between program behavior and performance on heterogeneous processors. These relationships are then fed into a modeling framework that attempts to predict the performance of similar classes of applications on different processors. Most significantly, this study identifies several non-intuitive relationships between program characteristics and demonstrates that it is possible to accurately model CUDA kernel performance using only metrics that are available before a kernel is executed.
(Andrew Kerr, Gregory Diamos and Sudakhar Yalamanchili: “Modeling GPU-CPU Workloads and Systems”. Proceedings of the Third Workshop on General-Purpose Computation on Graphics Processing Units (GPGPU-3), Pittsburgh, PA. Apr. 2010. PDF Link.)
From the press release:
NVIDIA Corp. today introduced NVIDIA® Nexus, the industry’s first development environment for massively parallel computing that is integrated into Microsoft Visual Studio, the world’s most popular development environment for Windows-based solutions and Web applications and services.
“NVIDIA Nexus is going to improve programmer productivity immediately,” said Tarek El Dokor at Edge 3 Technologies. “An integrated GPU and CPU development solution is something Edge 3 has needed for a long time. The fact that it’s integrated into the Visual Studio development environment drastically reduces the learning curve.”
NVIDIA Nexus radically improves productivity by enabling developers of GPU computing applications to use the popular Microsoft Visual Studio-based tools and workflow in a transparent manner, without having to create a separate version of the application that incorporates diagnostic software calls. NVIDIA Nexus also includes the ability to run the code remotely on a different computer. Nexus includes advanced tools for simultaneously analyzing efficiency, performance, and speed of both the graphics processing unit (GPU) and central processing unit (CPU) to give developers immediate insight into how co-processing affects their applications.
Nexus is composed of three components:
The OpenCL Best Practices Guide is already publicly available on CUDA Zone.
Details from the press release:
Leveraging the extensive performance instrumentation in NVIDIA’s OpenCL drivers and hardware performance signals designed into NVIDIA GPUs, the OpenCL Visual Profiler provides developers with insight into performance bottlenecks and opportunities for optimization.
Key features include:
- Profiling of actual hardware signals, kernel efficiency, and instruction issue rate
- Timing of memory copies between system memory and GPU dedicated memory
- Customizable graphs to help developers focus in on problem areas
- Basic auto-analysis to reveal warp serialization problems
- Easy import/export to CSV for custom analysis
NVIDIA has also prepared a helpful OpenCL Best Practices Guide designed to help OpenCL developers programming for the CUDA architecture implement high performance parallel algorithms and understand best practices for GPU Computing.