POPPUR爱换

 找回密码
 注册

QQ登录

只需一步,快速开始

手机号码,快捷登录

搜索
楼主: Edison
打印 上一主题 下一主题

NVIDIA 下一代架构"Fermi" 猜测、讨论专题

 关闭 [复制链接]
261#
发表于 2009-8-24 01:15 | 只看该作者
下一代呀下一代,到底选哪个好能ATI OR NV?
回复 支持 反对

使用道具 举报

262#
发表于 2009-8-25 04:35 | 只看该作者
希望NV 再来性价比高的产品
回复 支持 反对

使用道具 举报

263#
 楼主| 发表于 2009-8-26 13:41 | 只看该作者
Realworldtech DK 的关于未来 NVIDIA HPC GPU 的 ECC 内存应用可能性猜测:
http://www.realworldtech.com/page.cfm?ArticleID=RWT081909212132
回复 支持 反对

使用道具 举报

264#
 楼主| 发表于 2009-9-1 01:18 | 只看该作者
没了 NVISION,不过 GTC 的阵容似乎更加夸张。

1001 From Brook to CUDATalk
1002 Accelerating Energy Exploration and Production with Seismic ProcessingTalk
1003 Overview of Computational Finance on the GPUTalk
1004 Derivative Price Modeling on the GPUTalk
1005 OPLib: A GPL Library of Elementary Pricing Functions in CUDA/OpenCL and OpenMPTalk
1006 Implementing 3D Finite Difference Codes on the GPUTutorial
1007 Digital 3D EntertainmentTalk
1008 Memory Saving Discrete Fourier Transformation on CUDATalk
1009 Real Time Multi-Channel, Multi-Camera Image Processing using CUDATalk
1010 Volunteer Computing for GPUs: Petaflops for FreeTalk
1011 Have You Heard What a GPU Can Do? - A Revolution in Audio Talk
1012 MetaSL: Platform Independent Raster and Raytraced Rendering Talk
1013 Large Scale VisualizationTalk
1015 DirectCompute Tutorial
1016 MATLAB GPU Computing Essentials TutorialTutorial
1017 The Art of Debugging for the CUDA ArchitectureModerated Roundtable
1018 Sparse Linear Algebra - Iterative Solvers and Preconditioners on GPUs for Engineering SimulationsTalk
1019 CULA: Robust GPU Accelerated Linear Algebra LibrariesTalk
1020 Advances in GPU-based Image Processing and Computer VisionTalk
1022 High Performance Remote GraphicsTalk
1023 NEXUS: A Powerful IDE for GPU Computing on WindowsTalk
1024 Par4All: Auto-Parallelizing C and Fortran for the CUDA ArchitectureTalk
1025 Large-Scale Text Mining on the GPUModerated Roundtable
1026 Particle Filters and Sequential Monte Carlo Techniques Using GPUsTalk
1027 Banking on Monte CarloTalk
1028 Performance Primitives for Video Codec and Image Processing Talk
1029 C for CUDA - AdvancedTutorial
1030 GPU-based Libraries: Accelerating the Next Generation of ApplicationsPanel
1031 Designed for CUDA Program OverviewTalk
1032 Compute Application Testing Moderated Roundtable
1033 Using CUDA within MathematicaTutorial
1034 You Might Also Like: A Multi-GPU Recommendation SystemTalk
1035 Harnessing the GPU for Surgical Training and Preoperative PlanningTalk
1036 GPU Accelerated Solvers for ODEs Describing Cardiac Membrane EquationsTalk
1037 Mapping Satellite Imagery on the GPU: Fast Orthorectification and Pan-SharpeningTalk
1046 Research Summit Fast Forward with Bill DallyTalk
1047 Computer Vision with Horst BischofTalk
1048 Interactive Ray Tracing with the OptiX ray tracing engineTalk
1049 Supercomputing Super SessionPanel
1050 Quantum Chemistry on the GPU: Accelerating DFT CalculationsTalk
1051 GPU Accelerated Molecular Dynamics with AMBERTalk
1053 GPU Accelerated Visualization and Analysis in VMDTalk
1055 What Every CUDA Programmer Needs to Know About OpenGLTutorial
1056 Multiparticle Simulation Moderated Roundtable
1057 NEXUS: A Powerful IDE for GPU Computing on Windows Talk
1058 Tridiagonal Solvers on the GPU and Applications to Fluid SimulationTalk
1059 Fast Tridiagonal Solvers on GPUTalk
1060 Graphcuts with CUDA and Applications in Image ProcessingTalk
1061 Real-time Visual Effects in Film and Video: the GPU Changes EverythingTalk
1062 Astrophysical Fluid Simulation Using Adaptive MeshesTalk
1065 Diesel-Powered GPU Computing: Enabling a Real-Time Radio Telescope in the Australian OutbackTalk
1068 OpenCL OptimizationTutorial
1069 Zombies on Tegra: A Case Study in Mobile Augmented RealityTalk
1070 Face Recognition for Photographs and VideoTalk
1071 Face DetectionTalk
1073 Programming the Professional Video PipelineTutorial
1074 Computational Fluid Dynamics (CFD) for the GPUTalk
1075 Reconstructing the Brain: Extracting Neural Circuitry with CUDA and MPITalk
1076 Optimizing Ion Channel Kinetics Using A Massively Parallel Genetic Algorithm on the GPUTalk
1077 Bullet: A Case Study in Optimizing Physics Middleware for the GPUTalk
1078 Adobe Photoshop CS4 and GPUsTalk
1079 Scalable Multi Agent Simuluation on the GPUTalk
1080 The Art of Performance Tuning for the CUDA ArchitectureModerated Roundtable
1082 Advanced Numeric ComputingTalk
1083 CUDA Fortran Programming for NVIDIA GPUsTutorial
1084 The TotalView Debugger for CUDATalk
1085 Debugging Tools for CUDATalk
1086 Advanced C for CUDATutorial
1087 High Dynamic Range Spectral ImageryTalk
1088 Medical Image Registration with CUDATalk
1090 Spatial Data Structures for Massively Parallel ComputingTalk
1091 Clusters with GPUs under Linux and Windows HPCTalk
1098 Nexus LabHands-on tutorial
1100 Speed Limit Recognition System (Optimized for processing on the GPU) Talk
1101 GPU Computing in Java: Generation and Scheduling of PTX AssemblyTalk
1102 4D Volume RenderingTalk
1105 SQL/XML-IMDBg: A GPU In-Memory Database and Query Co-ProcessorTalk
1106 Driving on Mars: Simulating Tracked Vehicle Operation on Granular TerrainTalk
1108 Exploiting the GPU in Ultra High-End 4K Video ServersTalk
1109 Building a Modern Engine for the Visual Simulation IndustryTalk
1110 Using the GPU for Gradient Reconstruction of Unstructured MeshesTalk
1111 Industrial Simulation Using Massively Parallel AlgorithmsTalk
1112 Visualizing the Universe: Raycasting Astrophysical Simulation DataTalk
1113 Programming NVIDIA GPUs using PGI Accelerator Fortran and C CompilersTalk
1114 Strategies for GPU Acceleration of Common Visual Effects for Broadcast and Post-ProductionTalk
1122 Maximizing GPU Efficiency in Extreme Throughput ApplicationsTalk
1130 SCVF: A Framework for Visualization of Grid and Particle Based CUDA SimulationsTalk
1134 Using OpenKODE to Create a Seamless Driving ExperienceTalk
1138 Rigid Body, Cloth and Fluid Physics for CUDATalk
1139 CUDA Kernel Performance Analysis Using NVPerfMonTalk
1140 GPU Debugging Made Easy with DDTTalk
1141 Energy Industry Applications: Three Examples of GPU Acceleration in the Oil and Gas Industry Using CUDATalk
1142 Augmented Reality Talk
1200 Opening Keynote with Jen-Hsun Huang, CEO and Co-Founder, NVIDIA Keynote
1201 Visual Computing TrendsGeneral Session
1203 Using GPUs to Estimate the Value-at-Risk of PortfoliosTalk
1400 GPU Metaprogramming using PyCUDA: Methods & ApplicationsTalk
1401 Convolution Soup: A Case Study in CUDA OptimizationTalk
1402 Applications of Graphics Processing Units to the Binary Black Hole EvolutionsTalk
1404 Real Time Cloth: 3D Triangular Mesh Algorithms on the GPUTalk
1405 Adobe Premiere Pro CS4 and GPUs Talk
1406 Embedded Tesla-Using CUDA and Tesla in a Medical DeviceTalk
1407 OpenGL: The Train Has Left the StationTutorial
1408 DirectX 11 OverviewTutorial
1409 OpenCL on the GPUTutorial
1410 C on the GPUTutorial
1411 DirectComputeTutorial
1412 Languages, APIs and Development Tools for GPU ComputingTutorial
1415 Efficient Integration of CUDA & OpenGL Proccessing in XIPTalk
1417 Using Flash SVG Animations in Enhanced & Virtual RealityTalk
1418 Heterogeneous Multicore Parallel ProgrammingTalk
1419 Exhibits Open / Networking Happy Hour / Research Posters PreviewNetworking & Exhibits
1421 Exhibits Open / Networking Lunch (Thursday)Networking & Exhibits
1422 Day 2 Keynote with Hanspeter Pfister, Harvard UniversityKeynote
1423 Day 3 Keynote with Richard Kerris, LucasfilmKeynote
1425 Future Directions in GPU ComputingGeneral Session
1426 Fireside Chat with Jen-Hsun Huang and Jon PeddieGeneral Session
1428 Raising Capital in Difficult EnvironmentsGeneral Session
1432 CUDA Research Roundtable: Mixed Precision GPU Computing for High Precision Computational ScienceModerated Roundtable
1437 Directing Experiments in the International Space Station With GPU-Assisted Image AnalysisTalk
1441 Binary Black Holes using GPUsTalk
1442 Numerical Cosmology Powered by GPUsTalk
1443 Thrust: A Parallel Template Library for CUDATutorial
2001 Visioglobe Startup PresentationECS Startup Presentation
2002 Viewdle Inc. Startup PresentationECS Startup Presentation
2003 VERTICE Startup PresentationECS Startup Presentation
2004 TechniScan, Inc. Startup PresentationECS Startup Presentation
2005 Stormfjord Startup PresentationECS Startup Presentation
2006 SOFTKINETIC S.A. Startup PresentationECS Startup Presentation
2007 Realtime Technology AG Startup PresentationECS Startup Presentation
2008 Right Hemisphere Startup PresentationECS Startup Presentation
2009 OptiTex Startup PresentationECS Startup Presentation
2010 Nurien Software Startup PresentationECS Startup Presentation
2011 metaio, Inc. Startup PresentationECS Startup Presentation
2012 Innovative Converged Devices Ltd Startup PresentationECS Startup Presentation
2013 Forterra Systems, Inc Startup PresentationECS Startup Presentation
2014 Elemental Technologies, Inc. Startup PresentationECS Startup Presentation
2015 Edge 3 Technologies Startup PresentationECS Startup Presentation
2016 Cooliris Startup PresentationECS Startup Presentation
2017 Canesta Startup PresentationECS Startup Presentation
2018 C3 Technologies Startup PresentationECS Startup Presentation
2019 Aqumin LLC Startup PresentationECS Startup Presentation
2020 Acceleware Startup PresentationECS Startup Presentation
2021 Immersive MediaECS Startup Presentation
2022 NextIO Inc.ECS Startup Presentation
2023 Motus GamesECS Startup Presentation
2024 GASS Company for Advanced Supercomputing Solutions LTDECS Startup Presentation
2025 Visualization Sciences Group, IncECS Startup Presentation
2028 Teradici CorporationECS Startup Presentation
2029 MotionDSP Inc.ECS Startup Presentation
2030 MirriAdECS Startup Presentation
2031 Mirics Semiconductor Inc.ECS Startup Presentation
2032 MilabraECS Startup Presentation
2033 ICIDO GmbHECS Startup Presentation
2034 Hanweck Associates, LLCECS Startup Presentation
2035 DUX Soft Pvt. Ltd.ECS Startup Presentation
2036 Anark CorporationECS Startup Presentation
2037 AllegorithmicECS Startup Presentation
2038 Affine SystemsECS Startup Presentation
2039 HPC PROJECTECS Startup Presentation



大家留意 Brook to CUDA 的 Ian Buck ...
回复 支持 反对

使用道具 举报

265#
 楼主| 发表于 2009-9-1 01:20 | 只看该作者
Title:  Future Directions in GPU Computing
  
Length:  1 hour
Abstract:  Join our panel of leading industry experts as they discuss some of the most exciting and disruptive current and future applications to be built on top of GPUs. Topics will cover both visual and high performance computing, including rendering, video processing, scientific computing, cloud computing, and more. Industry analyst Rob Enderle will moderate this marquis panel, which will include Steve Perlman, Founder and CEO- ONLIVE; Simon Hayhurst, Senior Director of Product Management – Adobe; Sean Varah CEO- MotionDSP; and Bill Dally, NVIDIA’s Chief Scientist


这个也很对我的胃口。
回复 支持 反对

使用道具 举报

266#
 楼主| 发表于 2009-9-1 01:22 | 只看该作者
大家还可以留一下这个:

Title:  Debugging Tools for CUDA
  
Length:  30 Minutes
Abstract:  Explore the ease of debugging heterogeneous applications using the integrated CPU and GPU debugging environment of CUDA-GDB. CUDA-GDB is NVIDIA's very first native GPU debugger that lets you debug CUDA applications on the Linux platforms. In this session you will learn about the capabilities of the CUDA-GDB debugger with a walk through of the simplicities of being able to debug complex parallel applications. CUDA-GDB is also a platform to built custom debuggers so if you plan to build a CUDA debugger this session will provide the details on building your very own CUDA debugger.
Speaker:  Satish Salian CUDA Tools Manager
NVIDIA


Key Topics:  General Interest, Tools
回复 支持 反对

使用道具 举报

267#
 楼主| 发表于 2009-9-1 22:20 | 只看该作者
关于 Fermi 的最新消息是准备 9 月底完成工程样板,争取 12 月份上市,消息来源是 digitimes:

http://www.digitimes.com/news/a20090901PD204.html
回复 支持 反对

使用道具 举报

268#
发表于 2009-9-14 01:48 | 只看该作者
强烈的期待啊
回复 支持 反对

使用道具 举报

269#
 楼主| 发表于 2009-9-18 01:39 | 只看该作者
不日公开。

顺便提供外站一个不算太旧的所谓资料(夹杂着大量的猜测),没有经过证实。

http://www.associatedcontent.com ... _leaked.html?cat=15

40nm
32 SM
GDDR5 512-bit 3GHz+
Core Clock = 850MHz
DX11
OGL 3.1
CUDA 3.0
Release 2010 年 1 月


回复 支持 反对

使用道具 举报

270#
发表于 2009-9-18 09:07 | 只看该作者
本帖最后由 jhg1159 于 2009-9-18 09:15 编辑


技术实验GT200
MIMD
256/512  SP(8X/16XTPC)
64/128TMU
32ROP(64ROP)
GDDR5 256/512-bit 3.0GHz
Core Clock = 850MHz
DX11
回复 支持 反对

使用道具 举报

RacingPHT 该用户已被删除
271#
发表于 2009-9-18 22:51 | 只看该作者
提示: 作者被禁止或删除 内容自动屏蔽
回复 支持 反对

使用道具 举报

272#
发表于 2009-9-19 03:40 | 只看该作者
其實想想,以GT200/b的ROP在8x AA性能下降的問題來看,GT200/b直接搭GDDR5說不定性能上升也會蠻明顯的.......不過換成GDDR5以後頻寬實在一口氣增加太多了,TMU和ROP沒有大幅擴充實在太可惜。
而且為了CUDA的發展,也有必要考慮ECC....


總之,Fermi應該會有遠比RV770到RV870之間的差異更大的變更才對。
不過這些變更不見得都是針對繪圖就是了。和RV770到RV870之間的變更幾乎都在強化繪圖上有一些差距存在。
回复 支持 反对

使用道具 举报

273#
发表于 2009-9-19 08:38 | 只看该作者
其實想想,以GT200/b的ROP在8x AA性能下降的問題來看,GT200/b直接搭GDDR5說不定性能上升也會蠻明顯的.......不過換成GDDR5以後頻寬實在一口氣增加太多了,TMU和ROP沒有大幅擴充實在太可惜。
而且為了CUDA的發展,也 ...
Eji 发表于 2009-9-19 03:40


你的碎碎念最近怎么上不去了?
回复 支持 反对

使用道具 举报

274#
发表于 2009-9-19 17:04 | 只看该作者
277# 32nm

也得用代理了
回复 支持 反对

使用道具 举报

275#
发表于 2009-9-19 19:35 | 只看该作者
NV的高阶gpu目前从来没有发布即超过700mhz@core。。。850mhz换ati还是很有可能的
回复 支持 反对

使用道具 举报

276#
发表于 2009-9-19 20:48 | 只看该作者
279# 八角差开
对nv来说,gpu频率早就不重要了

请你看看shader频率
回复 支持 反对

使用道具 举报

277#
发表于 2009-9-19 20:51 | 只看该作者
279# 八角差开  
对nv来说,gpu频率早就不重要了

请你看看shader频率
yamhill 发表于 2009-9-19 20:48

850mhz就意味着shader频率可能至少在1700+
回复 支持 反对

使用道具 举报

278#
发表于 2009-9-19 22:20 | 只看该作者
你的碎碎念最近怎么上不去了?
32nm 发表于 2009-9-19 08:38


聽朋友講說被和諧了。
我明明沒寫什麼奇怪的東西.....XDa
回复 支持 反对

使用道具 举报

头像被屏蔽
279#
发表于 2009-9-20 22:34 | 只看该作者
提示: 作者被禁止或删除 内容自动屏蔽
回复 支持 反对

使用道具 举报

RacingPHT 该用户已被删除
280#
发表于 2009-9-21 00:05 | 只看该作者
提示: 作者被禁止或删除 内容自动屏蔽
回复 支持 反对

使用道具 举报

您需要登录后才可以回帖 登录 | 注册

本版积分规则

广告投放或合作|网站地图|处罚通告|

GMT+8, 2025-8-29 05:20

Powered by Discuz! X3.4

© 2001-2017 POPPUR.

快速回复 返回顶部 返回列表