bmv
|
|
Archangel
|
|
|
|
|
|
|
Рег.: 22.11.2003
|
|
Сообщений: 9597
|
|
Из: Universe
|
|
Рейтинг: 1431
|
|
Re: Новинки программного обеспечения
[re: bmv]
16.05.2009 05:11
|
|
|
CUDA Toolkit and SDK v2.2
A brief overview of features--there are a lot:
- Officially adds support for Windows 7, Server 2003, Server 2008, Ubuntu 8.10, RHEL 5.3, and Fedora 10
- Includes cuda-gdb (hardware GPU debugger) for RHEL5 32 and 64-bit (officially supported and tested), but it may work on more platforms than just those
- Exclusive device mode in Linux: set some GPUs as exclusive-compute (can only own a single CUDA context) and some as non-compute (no CUDA contexts allowed) for easier management of clusters/MPI applications. See the manpage for nvidia-smi for how to set this and cudaSetValidDevices in the reference manual on how to best use this from CUDART.
- Zero-copy support: transparently read from certain system memory from a kernel on GT200 or MCP79 systems. See this post for more information on how it works.
- Asynchronous memcpy support on Vista/Server 2008/Win7
- Texture from pitchlinear memory: use this to avoid an additional memcpy at times in some scenarios.
- >4GB of pinned memory in a single allocation on most OSes
- maximum pinned memory per allocation increased in Vista to ~1.5GB
- pinned memory can be shared between contexts
- Multi-device OpenGL interop performance between a Quadro display card and a separate compute card is dramatically improved.
- Visual Profiler works on Vista
- Visual Profiler supports additional counters for GT200 to measure number of memory transactions of a given size, instruction throughput, etc.
- Blocking sync support for all platforms: allows the host thread to sleep and be awoken by driver when the GPU operation the host thread is waiting on is completed.
- Quite a few additional math functions added due to forum requests (feel free to keep posting requests, we do pay attention)
- __threadfence(): ensure that a thread's pending memory writes are visible to all threads before continuing. It is explicitly not a global sync, unlike how it appears to some.
- Lots of bugfixes, of course; most importantly, killing a CUDA app should behave much, much better than it ever has before, especially when you're on a dedicated compute card
|
Transit-forever
Mageia Linux provider
|
|
|
bmv
|
|
Archangel
|
|
|
|
|
|
|
Рег.: 22.11.2003
|
|
Сообщений: 9597
|
|
Из: Universe
|
|
Рейтинг: 1431
|
|
Re: Новинки программного обеспечения
[re: bmv]
16.05.2009 07:17
|
|
|
New Features
--------------------------------------------------------------------------------
Hardware Support
o See http://www.nvidia.com/object/cuda_learn_products.html
Platform Support
o Additional OS support
- Red Hat Enterprise Linux 5.3
- SUSE Linux 11.1
- Fedora 10
- Ubuntu 8.10
o Eliminated OS support
- SUSE Linux 10.3
- Fedora 8
- Ubuntu 7.10
API Features
o Pinned Memory Support
- These new memory management functions (cuMemHostAlloc() and
cudaHostAlloc()) enable pinned memory to be made "portable" (available
to all CUDA contexts), "mapped" (mapped into the CUDA address space),
and/or "write combined" (not cached and faster for the GPU to access).
- cuMemHostAlloc
- cuMemHostGetDevicePointer
- cudaHostAlloc
- cudaHostGetDevicePointer
o Function attribute query
- This function allows applications to query various function properties.
- cuFuncGetAttribute
o 2D Texture reads from pitch linear memory
- You can bind linear memory that you get from cuMemAlloc() or
cudaMalloc() directly to a 2D texture. In previous releases, you were
only able to bind cuArrayCreate() or cudaMallocArray() arrays to 2D
textures.
- cuTexRefSetAddress2D
- cudaBindTexture2D
o Flags for event creation
- Applications can now create events that use blocking synchronization.
- cudaEventCreateWithFlags
o New device management and context creation flags
- The function cudaSetDeviceFlags() allows the application to specify
attributes such as mapping host memory and support for blocking
synchronization.
- cudaSetDeviceFlags
o Improved runtime device management
- The runtime now defaults to attempting context creation on other
devices in the system before returning any failure messages. The new
call cudaSetValidDevices() allows the application to specify a list of
acceptable devices for use.
- cudaSetValidDevices
o Driver/runtime version query functions
- Applications can now directly query version information about the
underlying driver/runtime.
- cuDriverGetVersion
- cudaDriverGetVersion
- cudaRuntimeGetVersion
o New device attribute queries
- CU_DEVICE_ATTRIBUTE_INTEGRATED
- CU_DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY
- CU_DEVICE_ATTRIBUTE_COMPUTE_MODE
Documentation
o Doxygen-generated and cross-referenced html, pdf, and man pages.
- Runtime API
- Driver API
|
Transit-forever
Mageia Linux provider
|
|
|
bmv
|
|
Archangel
|
|
|
|
|
|
|
Рег.: 22.11.2003
|
|
Сообщений: 9597
|
|
Из: Universe
|
|
Рейтинг: 1431
|
|
Re: Новинки программного обеспечения
[re: bmv]
22.06.2009 19:26
|
|
|
Бета версия CUDA SDK 2.3 и видеодрайвера Nvidia 190.09
В рассылке разработчиков компания Nvidia сообщила о выпуске бета версии среды разработки, утилит и драйвера с поддержкой новых функций CUDA 2.3 (Compute Unified Device Architecture - API, разработанное компанией NVidia и позволяющее вынести некоторые вычислительные задачи на плечи GPU) Среди новшеств и изменений следует отметить:
* Библиотека CUFFT теперь поддерживает преобразования двойной точности, значительное улучшение производительности для преобразований одиночной точности.
* CUDA-GDB - аппаратных отладчик, теперь доступен на всех поддерживаемых платформах Linux и входит в состав CUDA Toolkit.
* GPUs в SLI группах, теперь, нумеруются в индивидуально, так, что вы можете достичь производительность нескольких GPU, даже при включенной SLI для графики.
* Новая поддержка преобразования между fp16 и intrinsics, позволяет хранить данные fp16 в формате fp32. Использование fp16 формата идеально подходит для приложений, требующих больший числовой диапазон, чем 16-битное целое, но менее точной, чем fp32, этим уменьшая объем используемой памяти и потребление пропускной способности.
* Новая pitchLinearTexure и пример кода, который показывает, насколько эффективно использовать текстуры из поля линейной памяти.
* Новый PTXJIT пример, иллюстрирующий, как использовать cuModuleLoadDataEx() для загрузки PTX источники из памяти, вместо загрузки файла.
* Два новых примера для Windows, показывающих, как использовать библиотеку NVCUVID для декодирования MPEG-2, VC-1 и H.264 данных и передавать кадры для отображения с помощью OpenGL и Direct3D
* Обновлены примеры показывающие, как правильно выравнивать параметры функций ядра CUDA, так, чтоб один и тот же код работал на x32 и x64 системах.
* В Visual Profiler в CUDA Toolkit имеет некоторые проблемы, которые были обнаружены слишком поздно, чтобы исправить без задержки бета-релиза. Пожалуйста, используйте вариант, который устанавливается отдельно (вне Toolkit) путем установки инструментальных средств, а затем отдельно установкой Visual Profiler поверх.
* Драйвер для CUDA в MacOS, теперь упаковываются отдельно от CUDA Toolkit.
* Поддержка основных дистрибутивов Linux, MacOS X, и Windows: Fedora 10, RHEL 4.7 & 5.3, SLED 10.2 & 11.0, OpenSUSE 11.1, и Ubuntu 8.10 & 9.04 Windows XP/Vista/7 с Visual Studio 8 (VC2005) и 9 (VC2008) MacOS X 10.5.6 и позже (32-bit).
В состав SDK также включена бета версия видеодрайвера Nvidia 190.09 (для загрузки необходима регистрация на сайте nvdeveloper.nvidia.com), в которой отмечены следующие улучшения:
* Исправлены некоторые ошибки при работе приложений в Compiz/Beryl, в частности устранены проблемы при работе в Kopete;
* Исправлены нарушения отображения при просмотре/декодировании H.264 и VC-1 на картах с процессором G98 и MCP7;
* Улучшена обработка битых и неправильных байт в H.264 на ядрах G84, G86, G92, G94, G96, или GT200;
* Исправлена проблема, приводившая к падению X-сервера, при переключении консолей;
* Улучшено определение совместимости видеокарты с VDPAU.
http://www.opennet.ru/opennews/art.shtml?num=22243
|
Transit-forever
Mageia Linux provider
|
|
|
bmv
|
|
Archangel
|
|
|
|
|
|
|
Рег.: 22.11.2003
|
|
Сообщений: 9597
|
|
Из: Universe
|
|
Рейтинг: 1431
|
|
Re: Новинки программного обеспечения
[re: bmv]
20.03.2010 20:53
|
|
|
CUDA 3.0
Release Highlights
* Support for the new Fermi architecture, with:
o Native 64-bit GPU support
o Multiple Copy Engine support
o ECC reporting
o Concurrent Kernel Execution
o Fermi HW debugging support in cuda-gdb
o Fermi HW profiling support for CUDA C and OpenCL in Visual Profiler
* C++ Class Inheritance and Template Inheritance support for increased programmer productivity
* A new unified interoperability API for Direct3D and OpenGL, with support for:
o OpenGL texture interop
o Direct3D 11 interop support
* CUDA Driver / Runtime Buffer Interoperability, which allows applications using the CUDA Driver API to also use libraries implemented using the CUDA C Runtime such as CUFFT and CUBLAS.
* CUBLAS now supports all BLAS1, 2, and 3 routines including those for single and double precision complex numbers
* Up to 100x performance improvement while debugging applications with cuda-gdb
* cuda-gdb hardware debugging support for applications that use the CUDA Driver API
* cuda-gdb support for JIT-compiled kernels
* New CUDA Memory Checker reports misalignment and out of bounds errors, available as a stand-alone utility and debugging mode within cuda-gdb
* CUDA Toolkit libraries are now versioned, enabling applications to require a specific version, support multiple versions explicitly, etc.
* CUDA C/C++ kernels are now compiled to standard ELF format
* Support for device emulation mode has been packaged in a separate version of the CUDA C Runtime (CUDART), and is deprecated in this release. Now that more sophisticated hardware debugging tools are available and more are on the way, NVIDIA will be focusing on supporting these tools instead of the legacy device emulation functionality.
o On Windows, use the new Parallel Nsight development environment for Visual Studio, with integrated GPU debugging and profiling tools (was code-named "Nexus"). Please see www.nvidia.com/nsight for details.
o On Linux, use cuda-gdb and cuda-memcheck, and check out the solutions from Allinea and TotalView that will be available soon.
* Support for all the OpenCL features in the latest R195 production driver package:
o Double Precision
o Graphics Interoperability with OpenCL, Direc3D9, Direct3D10, and Direct3D11 for high performance visualization
o o Query for Compute Capability, so you can target optimizations for GPU architectures (cl_nv_device_attribute_query)
o Ability to control compiler optimization settings via support for pragma unroll in OpenCL kernels and an extension that allows programmers to set compiler flags. (cl_nv_compiler_options)
o OpenCL Images support, for better/faster image filtering
o 32-bit global and local atomics for fast, convenient data manipulation
o Byte Addressable Stores, for faster video/image processing and compression algorithms
o Support for the latest OpenCL spec revision 1.0.48 and latest official Khronos OpenCL headers as of 2010-02-17
http://developer.nvidia.com/object/cuda_3_0_downloads.html
|
Transit-forever
Mageia Linux provider
|
|
|
bmv
|
|
Archangel
|
|
|
|
|
|
|
Рег.: 22.11.2003
|
|
Сообщений: 9597
|
|
Из: Universe
|
|
Рейтинг: 1431
|
|
Re: Новинки программного обеспечения
[re: bmv]
20.11.2010 18:04
|
|
|
CUDA Toolkit 3.2
New and Improved CUDA Libraries
* CUBLAS performance improved 50% to 300% on Fermi architecture GPUs, for matrix multiplication of all datatypes and transpose variations
* CUFFT performance tuned for radix-3, -5, and -7 transform sizes on Fermi architecture GPUs, now 2x to 10x faster than MKL
* New CUSPARSE library of GPU-accelerated sparse matrix routines for sparse/sparse and dense/sparse operations delivers 5x to 30x faster performance than MKL
* New CURAND library of GPU-accelerated random number generation (RNG) routines, supporting Sobol quasi-random and XORWOW pseudo-random routines at 10x to 20x faster than similar routines in MKL
* H.264 encode/decode libraries now included in the CUDA Toolkit
CUDA Driver & CUDA C Runtime
* Support for new 6GB Quadro and Tesla products
* New support for enabling high performance Tesla Compute Cluster (TCC) mode on Tesla GPUs in Windows desktop workstations
Development Tools
* Multi-GPU debugging support for both cuda-gdb and Parallel Nsight
* Expanded cuda-memcheck support for all Fermi architecture GPUs
* NVCC support for Intel C Compiler (ICC) v11.1 on 64-bit Linux distros
* Support for debugging GPUs with more than 4GB device memory
Miscellaneous
* Support for memory management using malloc() and free() in CUDA C compute kernels
* New NVIDIA System Management Interface (nvidia-smi) support for reporting % GPU busy, and several GPU performance counters
New GPU Computing SDK Code Samples
* Several code samples demonstrating how to use the new CURAND library, including MonteCarloCURAND, EstimatePiInlineP, EstimatePiInlineQ, EstimatePiP, EstimatePiQ, SingleAsianOptionP, and randomFog
* Conjugate Gradient Solver, demonstrating the use of CUBLAS and CUSPARSE in the same application
* Function Pointers, a sample that shows how to use function pointers to implement the Sobel Edge Detection filter for 8-bit monochrome images
* Interval Computing, demonstrating the use of interval arithmetic operators using C++ templates and recursion
* Simple Printf, demonstrating best practices for using both printf and cuprintf in compute kernels
* Bilateral Filter, an edge-preserving non-linear smoothing filter for image recovery and denoising implemented in CUDA C with OpenGL rendering
* SLI with Direct3D Texture, a simple example demonstrating the use of SLI and Direct3D interoperability with CUDA C
* cudaEncode, showing how to use the NVIDIA H.264 Encoding Library using YUV frames as input
* Vflocking Direct3D/CUDA, which simulates and visualizes the flocking behavior of birds in flight
* simpleSurfaceWrite, demonstrating how CUDA kernels can write to 2D surfaces on Fermi GPUs
|
Transit-forever
Mageia Linux provider
|
|
|
|
Список
Плоский
Дерево
