Please login or register.
1 Hour 1 Day 1 Week 1 Month Forever
Login with username, password and session length

This section allows you to view all posts made by this member. Note that you can only see posts made in areas you currently have access to.

1

3D-Tech News Around The Web / NVIDIA CUDA 5.5 Release Candidate Now Available For Download

« on: June 18, 2013, 10:26:15 PM »

CUDA 5.5 Release Candidate Now Available For Download

Optimized for MPI Applications

    Enhanced Hyper-Q support for multiple MPI processes via the new Multi-Process Service (MPS) on Linux systems
    MPI Workload Prioritization enabled by CUDA stream prioritization
    Multi-process MPI debugging & profiling

Guided Performance Analysis

    Step-by-step guidance helps you identify performance bottlenecks and apply optimizations in the NVIDIA Visual Profile and Nsight, Eclipse Edition

Support for ARM Platforms

    Native compilation, for easy application porting
    Fast cross-compile on x86 for large applications

More Highlights

    Single GPU debugging for Linux
    Static CUDA runtime library
    RPM/DEB packaging & new NVIDIA repo

2

3D-Tech News Around The Web / NVIDIA Quadro/Tesla driver 320.27 WHQL

« on: June 17, 2013, 07:22:37 PM »

Changes in Version 320.27
The following sections list the important changes and the most common issues resolved
since driver version 320.00.
Windows Vista/Windows 7 Fixed Issues
 [Catia]: Poor performance is experienced with new Catia render engine.
 [AVID Motion Graphics/Brainstorm]: Frame rate stutter occurs when a highly
tessellated sphere goes off screen and then comes back on screen.
 [Quadro 5000/K5000][VizRT]: OpenGL performance regression occurs with recent
drivers.
 [Catia]: The application occasionally crashes after attaching a debugger.
 [Avid Motion Graphics]: The application shows additional CPU activity and reduced
performance when GPUD4V is utilized to transfer frames/fields to the AJA video I/O
device.
 [Avid Motion Graphics]: Higher CPU usage occurs when running the application
with GPUD4V transfers when compared to PBO transfers.
 [Avid Motion Graphics]: The application profile does not get applied.
 [Avid Motion Graphics]: There is a decrease in application performance when the
material editor is displayed.

   DEV_0197 "NVIDIA Tesla C870"
   DEV_019D "NVIDIA Quadro FX 5600"
   DEV_019E "NVIDIA Quadro FX 4600"
   DEV_040A "NVIDIA Quadro FX 370"
   DEV_040D "NVIDIA Quadro FX 1600M"
   DEV_040E "NVIDIA Quadro FX 570"
   DEV_040F "NVIDIA Quadro FX 1700"
   DEV_042F "NVIDIA Quadro NVS 290"
   DEV_05E7 "NVIDIA Tesla C1060"
   DEV_05E7&SUBSYS_059510DE "NVIDIA Tesla T10 Processor"
   DEV_05E7&SUBSYS_066A10DE "NVIDIA Tesla C1060 "
   DEV_05E7&SUBSYS_068F10DE "NVIDIA Tesla T10 Processor "
   DEV_05E7&SUBSYS_069710DE "NVIDIA Tesla M1060"
   DEV_05E7&SUBSYS_071410DE "NVIDIA Tesla M1060 "
   DEV_05E7&SUBSYS_074310DE "NVIDIA Tesla M1060  "
   DEV_05F9 "NVIDIA Quadro CX"
   DEV_05FD "NVIDIA Quadro FX 5800"
   DEV_05FE "NVIDIA Quadro FX 4800"
   DEV_05FF "NVIDIA Quadro FX 3800"
   DEV_0619 "NVIDIA Quadro FX 4700 X2"
   DEV_061A "NVIDIA Quadro FX 3700"
   DEV_061B "NVIDIA Quadro VX 200"
   DEV_061C "NVIDIA Quadro FX 3600M"
   DEV_061D "NVIDIA Quadro FX 2800M"
   DEV_0638 "NVIDIA Quadro FX 1800"
   DEV_0658 "NVIDIA Quadro FX 380"
   DEV_0659 "NVIDIA Quadro FX 580"
   DEV_065C "NVIDIA Quadro FX 770M"
   DEV_06D1 "NVIDIA Tesla C2050 / C2070"
   DEV_06D1&SUBSYS_077110DE "NVIDIA Tesla C2050"
   DEV_06D1&SUBSYS_077210DE "NVIDIA Tesla C2070"
   DEV_06D2 "NVIDIA Tesla M2070"
   DEV_06D2&SUBSYS_077410DE "NVIDIA Tesla M2070 "
   DEV_06D2&SUBSYS_083010DE "NVIDIA Tesla M2070  "
   DEV_06D2&SUBSYS_084210DE "NVIDIA Tesla M2070   "
   DEV_06D2&SUBSYS_088F10DE "NVIDIA Tesla X2070"
   DEV_06D2&SUBSYS_090810DE "NVIDIA Tesla M2070    "
   DEV_06D8 "NVIDIA Quadro 6000"
   DEV_06D9 "NVIDIA Quadro 5000"
   DEV_06DC "NVIDIA Quadro 6000  "
   DEV_06DD "NVIDIA Quadro 4000"
   DEV_06DE "NVIDIA Tesla T20 Processor"
   DEV_06DE&SUBSYS_077310DE "NVIDIA Tesla S2050"
   DEV_06DE&SUBSYS_082F10DE "NVIDIA Tesla M2050"
   DEV_06DE&SUBSYS_084010DE "NVIDIA Tesla X2070 "
   DEV_06DE&SUBSYS_084210DE "NVIDIA Tesla M2050 "
   DEV_06DE&SUBSYS_084610DE "NVIDIA Tesla M2050  "
   DEV_06DE&SUBSYS_086610DE "NVIDIA Tesla M2050   "
   DEV_06DE&SUBSYS_090710DE "NVIDIA Tesla M2050    "
   DEV_06DE&SUBSYS_091E10DE "NVIDIA Tesla M2050     "
   DEV_06DF "NVIDIA Tesla M2070-Q"
   DEV_06DF&SUBSYS_084D10DE "NVIDIA Tesla M2070-Q "
   DEV_06DF&SUBSYS_087F10DE "NVIDIA Tesla M2070-Q  "
   DEV_06F8 "NVIDIA Quadro NVS 420"
   DEV_06F9 "NVIDIA Quadro FX 370 LP"
   DEV_06FA "NVIDIA Quadro NVS 450"
   DEV_06FB "NVIDIA Quadro FX 370M"
   DEV_06FD "NVIDIA Quadro NVS 295"
   DEV_06FF "NVIDIA HICx16 + Graphics"
   DEV_06FF&SUBSYS_071110DE "NVIDIA HICx8 + Graphics"
   DEV_0A38 "NVIDIA Quadro 400"
   DEV_0A3C "NVIDIA Quadro FX 880M"
   DEV_0A78 "NVIDIA Quadro FX 380 LP"
   DEV_0DD8 "NVIDIA Quadro 2000"
   DEV_0DD8&SUBSYS_091410DE "NVIDIA Quadro 2000D"
   DEV_0DF8 "NVIDIA Quadro 600"
   DEV_0DF9 "NVIDIA Quadro 500M"
   DEV_0DFA "NVIDIA Quadro 1000M"
   DEV_0E3A "NVIDIA Quadro 3000M"
   DEV_0E3B "NVIDIA Quadro 4000M"
   DEV_0FF2 "NVIDIA GRID K1"
   DEV_0FF9 "NVIDIA Quadro K2000D"
   DEV_0FFA "NVIDIA Quadro K600"
   DEV_0FFD "NVIDIA NVS 510"
   DEV_0FFE "NVIDIA Quadro K2000"
   DEV_0FFF "NVIDIA Quadro 410"
   DEV_1021 "NVIDIA Tesla K20Xm"
   DEV_1022 "NVIDIA Tesla K20c"
   DEV_1028 "NVIDIA Tesla K20m"
   DEV_107C "NVIDIA NVS 315"
   DEV_107D "NVIDIA NVS 310"
   DEV_1091 "NVIDIA Tesla M2090"
   DEV_1091&SUBSYS_088710DE "NVIDIA Tesla M2090 "
   DEV_1091&SUBSYS_088E10DE "NVIDIA Tesla X2090"
   DEV_1091&SUBSYS_089110DE "NVIDIA Tesla X2090 "
   DEV_1094 "NVIDIA Tesla M2075"
   DEV_1094&SUBSYS_088810DE "NVIDIA Tesla M2075 "
   DEV_1096 "NVIDIA Tesla C2075"
   DEV_1096&SUBSYS_091010DE "NVIDIA Tesla C2075 "
   DEV_1096&SUBSYS_091110DE "NVIDIA Tesla C2050 "
   DEV_109B "NVIDIA Quadro 7000"
   DEV_109B&SUBSYS_091810DE "NVIDIA Quadro 7000 "
   DEV_10D8 "NVIDIA NVS 300"
   DEV_118F "NVIDIA Tesla K10"
   DEV_11BA "NVIDIA Quadro K5000"
   DEV_11BC "NVIDIA Quadro K5000M"
   DEV_11BD "NVIDIA Quadro K4000M"
   DEV_11BE "NVIDIA Quadro K3000M"
   DEV_11BF "NVIDIA GRID K2"
   DEV_11FA "NVIDIA Quadro K4000"
   DEV_087A "NVIDIA GeForce 9400    "
   DEV_06FF "NVIDIA HICx16 + Graphics"
   DEV_06FF&SUBSYS_071110DE "NVIDIA HICx8 + Graphics"
   DEV_06FF "NVIDIA HICx16 + Graphics"
   DEV_06FF&SUBSYS_071110DE "NVIDIA HICx8 + Graphics"

3

3D-Tech News Around The Web / (Android) DEAD TRIGGER 2 - TEGRA 4 Features

« on: June 16, 2013, 07:09:40 PM »

Check out the new DEAD TRIGGER 2 Teaser presenting the amazing graphic effects to be delivered on mobile devices in our upcoming global zombie shooter game!

DEAD TRIGGER 2 is coming...
Summer 2013.
Get ready for the time when zombies become part of our lives!

4

3D-Tech News Around The Web / Microsoft DirectXTex Update 1.1

« on: June 16, 2013, 10:49:42 AM »

The DirectX Texture library (aka DirectXTex) for Direct3D 11 (originally released on this blog and made an official CodePlex project) has continued to improve. It’s been a busy month of work, but with this release I’ve hit a milestone of sorts so I’m declaring this DirectXTex “Version 1.1”. This release includes custom filtering implementations to fully finish out the feature set, and as of this release all the functionality that was in D3DX11 for texture processing is now available in DirectXTex. Resizing and mipmap generation has been updated to avoid a number of known issues with the Windows Imaging Component (WIC) including proper HDR/XR format handling, sRGB gamma correct filtering and conversion behavior, mirror/wrap texture address mode filtering semantics, and implements the finite low-pass triangle filter that was available in D3DX. Volume map mipmap generation now supports all filtering modes and supports non-power-of-2 volume maps.

5

3D-Tech News Around The Web / CPU-Z for Android released

« on: June 14, 2013, 10:08:46 PM »

Android version of the popular CPU identification tool for PC/Windows., CPU-Z is a free application that reports information about your device.

- SoC (System On Chip) name, architecture, clock speed for each core ;
- System information : device brand & model, screen resolution, RAM, storage.;
- Battery information : level, status, temperature ;
- Sensors.

6

3D-Tech News Around The Web / NVIDIA Quadro & GeForce Mac OS X Driver Release 313.01.02

« on: June 13, 2013, 09:36:25 PM »

"New in Release 313.01.02f01:

    Contains performance improvements and bug fixes for a wide range of applications.
    Includes new NVIDIA Driver Manager preference pane."

Direct download links:
OpenGL driver
CUDA driver 5.0.61 (libcuda_313.01.02.dylib)

7

3D-Tech News Around The Web / Unigine - Rescue Helicopter Demo video

« on: June 13, 2013, 02:38:47 PM »

New Rescue Helicopter Demo Preview

June 12, 2013

UNIGINE Corp. sets a new visual standard in the simulation and training industry with a preview of its next-generation technology demo. The project has the cutting-edge UNIGINE Engine under the hood and showcases a simulation of a rescue helicopter operation with an extreme level of detail while running on consumer-level hardware. Read more in the official press-release.

8

3D-Tech News Around The Web / Unigine - Procedural Content Generation in Oil Rush

« on: June 13, 2013, 02:37:13 PM »

An Article on Procedural Content Generation in Oil Rush

We continue to share the experience of UNIGINE Corp. team in creating interactive real-time 3D worlds. A new article from our technical artists about some techniques used in development of Oil Rush naval strategy game is published, it contains a set of re-usable filters available for download. Read the article: Procedural Content Generation for Real-Time 3D Applications Part 1: Oil Rush

9

3D-Tech News Around The Web / PhysX videos from E3 @ Tweaktown

« on: June 12, 2013, 07:19:20 PM »

Epic's tech demo of Unreal Engine 4 makes use of NVIDIA PhysX technology, caught on video at E3


Sony Online Entertainment lets us see just how much PhysX improves their game at E3

We capture in-game footage of the upcoming Splinter Cell Blacklist game at E3

NVIDIA demoed Fur technology that is being used in The Witcher 3

10

3D-Tech News Around The Web / Microsoft Surface Pro firmware and driver pack June 2013

« on: June 12, 2013, 01:48:28 PM »

Cumulative firmware and drivers for the Surface Pro.

This firmware and driver package contains drivers for all of the components in the Surface Pro device, as well as updates to the system firmware that have been released via Windows Update.

These drivers and firmware are not compatible with Surface RT.

11

3D-Tech News Around The Web / Apple announces iOS 7 and OS X Mavericks

« on: June 10, 2013, 09:32:16 PM »

Latest Press Releases 06/10/2013
    Apple Unveils iOS 7
    Apple Announces iTunes Radio
    Apple Releases Developer Preview of OS X Mavericks With More Than 200 New Features
    Apple Brings All Day Battery Life to MacBook Air
    Apple Gives Sneak Peek Into the Future of the Pro Desktop

So far i found only one technical whitepaper, i'll recheck later...

OS X Mavericks Core Technologies Overview

12

3D-Tech News Around The Web / Unigine teases new demo "Rescue Helicopter Simulator"

« on: June 10, 2013, 01:42:54 PM »

Development log: June 08, 2013

Rescue Helicopter Simulator

UNIGINE Engine has been using in training and simulation field for several years, so we've decided to make our own simulation demo. At ITEC 2013 in Rome we showcased the preview of a new rescue helicopter simulation.

 Features of the demo:

    Huge open space: 262x262 km
    Real geospatial data
    Urban terrain simulation
    Dynamic weather
    Large visibility distance: 40 km
    Supersonic camera speed
    Extremely detailed close-up view
    Advanced light scattering model
    Double precision of coordinates
    Volumetric clouds
    Day/night cycle

 We'll publish the video teaser quite soon, so you'll be able to see the details.

13

3D-Tech News Around The Web / VLC media player 2.07 released

« on: June 10, 2013, 01:18:05 PM »

VLC 2.0.7 "Twoflower" is a small update to our 2.0 media player.

2.0.7 is a small update that fixes some regressions of the 2.0.x branch of VLC.
2.0.7 fixes track selection for PowerPC machines.
2.0.7 also fixes and important regression in decoding numerous audio file formats and when encoding in MP3 and AAC.
2.0.7 closes a couple of security issues and fixes regression in our ActiveX plugin for Internet Explorer.
With faster decoding on multi-core, GPU, and mobile hardware and the ability to open more formats, notably professional, HD and 10bits codecs, 2.0 was a major upgrade for VLC.

14

3D-Tech News Around The Web / (WebGL) 300000 Animated Cubes

« on: June 08, 2013, 04:06:23 PM »

300,000 gpu animated cubes - 3.6M triangles

An update to AlteredQualia's 1.8M triangle Animated Cube demo to use indexed interleaved geometry and increase double the cube count.

The framerate is of course dependent on your hardware.
If you get a black screen with Chrome 28, it's because of the new render engine.

15

3D-Tech News Around The Web / Intel Graphics Performance Analyzers Version 2013 R2

« on: June 08, 2013, 04:46:16 AM »

Available now, Intel GPA 2013 R2 adds these key features:

    Added support for the fourth generation of Intel® Core™ processors, including the following graphics systems: Intel® HD Graphics 5000/ 4600 / 4400 / 4200, Intel® Iris™ graphics 5100, and Intel® Iris™ Pro graphics 5200. A full list of the metrics available on these graphics systems can be found in the Intel GPA Online Help.

    Improved Render Target workflow in Intel GPA Frame Analyzer:
        An enhanced highlighting mode has been added for viewing render targets, buffers, and render target regions in the erg chart.
        A better selection method has been implemented for the Pixel History feature.
        A new button has been added to automatically transition from “large view” to “normal view” when the Pixel History tab is active.
        When using the Working View panel, after selecting a pixel the Pixel History tab is automatically engaged and displays a zoomed-in view of the selection.
    Added support of Android* OS version 4.2 target applications.
    Media performance metrics have now been integrated into the Intel GPA System Analyzer.
    Added a StretchRect tab that shows the surfaces before and after a StretchRect() call (only available for analyzing applications that use Microsoft* DirectX* 9).

16

3D-Tech News Around The Web / NVIDIA - Develop on your Notebook with GeForce, Deploy on Tesla

« on: June 08, 2013, 04:36:54 AM »

Develop on your Notebook with GeForce, Deploy on Tesla

"There’s a new post over on the NVIDIA Corporate Blog by my colleague Mark Ebersole about the latest line laptops powered by new GeForce 700-series GPUs. As Mark explains, the GeForce 700 series (GT 730M, GT 735M, and GT 740M), powered by the low-power GK208 GPU has the latest compute features of the Tesla K20 (powered by the GK110 GPU), including:

    CUDA Dynamic Parallelism, which enables the CUDA runtime API inside device code, so that threads running on the GPU can launch other kernels, call cudaMemcpy, create streams and events, and synchronize the device;
    Hyper-Q for CUDA Streams, which improves the efficiency and performance of concurrent kernels running on a single GPU;
    the SHFL warp shuffle instruction, which enables threads in the same warp to communicate directly; and
    up to 255 registers per thread (increased from 63 in the Fermi architecture), which can reduce bottlenecks caused by spilling registers to off-chip memory.

The availability of the latest GPU architecture on low-cost, highly portable laptops makes it possible to develop CUDA code that uses the latest performance features for deployment on high-end Tesla GPUs. Check out Mark’s blog post for more information."

17

3D-Tech News Around The Web / AMD GPUPerfAPI 2.11

« on: June 08, 2013, 04:18:52 AM »

Version 2.11 (6/5/13)

    Add support for AMD Radeon HD 8000 Series hardware.
    Add support for more AMD Radeon HD 7000 Series devices.
    Add support for more FirePro, Mobility, and APU devices.
    Improved performance and counter results when large numbers of counters are enabled on AMD Radeon HD 7000 Series hardware and newer.
    Improved counter results on systems with both an APU and a discrete GPU.
    DirectX 11:
        CSFetchInsts, CSTexBusy, and CSALUFetchRatio now report correct value on AMD Radeon HD 5000-6000 Series hardware.
    OpenGL/DirectX 10/DirectX 11:
        TexUnitBusy counter now reports correct value on AMD Radeon HD 7000 Series hardware.
    OpenCL:
        WriteSize counter now reports correct value on AMD Radeon HD 7000 Series hardware.

18

3D-Tech News Around The Web / AMD GPU PerfStudio 2.13

« on: June 08, 2013, 04:14:30 AM »

GPU PerfStudio 2.13 Improvements

    New feature “PerfMarker View”. A new tree control has been added to the Frame Debugger for easy viewing and navigation of Direct3D performance markers (D3DPERF_BeginEvent and D3DPERF_EndEvent)
        It displays perfmarker blocks as nested tree items making it easy to navigate the frame based on the structure of your perfmarkers
        The individual draw calls within perfmarker blocks are shown by default and can be turned off if required
        The GPUTime for perfmarker blocks and individual draw calls can be displayed
        The rows can be ordered by draw call index to allow the user to navigate by draw call index
        The rows can also be ordered by GPU Time to identify the most expensive perfmarker blocks and draw calls
        The perfmarkers can be expanded and collapsed by using the right click context menu
        Perfmarker blocks and individual draw calls can be re-profiled on demand
    Profiler support for latest AMD GPUs
    Fix for DX10 profiler counters on Southern Islands GPUs
    Option to disable the synching of the Frame Debugger, API Trace, and Profiler results windows

19

3D-Tech News Around The Web / NVIDIA Tegra Android Developer Pack 2.0r4

« on: May 29, 2013, 10:13:38 PM »

Tegra Android Developer Pack 2.0r4

    Setting up an Android development environment can be a complex and frustrating experience. NVIDIA simplifies this for all Android developers with a single installer that manages this complexity for you. The Tegra Android Development Pack installs all software tools required to develop for Android on NVIDIA’s Tegra platform and is the perfect companion for developing native applications for Tegra DevKits. This suite of developer tools is targeted at Tegra devices, but will configure a development environment that will work with almost any Android device.

Yet no Tegra 4 support 

20

3D-Tech News Around The Web / ARM - Benchmarking floating-point precision in mobile GPUs

« on: May 29, 2013, 09:56:58 PM »

When we talk about GPU performance (which we do a lot, here at Mali Central), we usually talk about speed. In previous blogs we’ve talked about how many pixels per second you can put on the screen, how many triangles per second you can pretend to draw (don’t ask), and most recently, how many floating-point operations per second you can issue. Talking about speed is great fun, and we love doing it, but it isn’t the only interesting GPU performance metric; quality also counts. After all, it doesn’t matter how fast you compute something if you get the wrong answer. In my next few blogs, I’ll let go (temporarily) of my obsession with speed, and talk about benchmarking the quality of GPU floating-point arithmetic. I have a lot to cover, so this is unavoidably long. Save it up for when you can concentrate.

But first, a rant…
Using floating point arithmetic is tricky. A lot of programmers, even some very good ones, don’t really understand it. Quite innocent-looking pieces of code can turn around and bite you, and it is often very hard to figure out why you’re getting bitten. That’s a problem even when you’re coding for nice, well-behaved, IEEE-754-compliant CPUs. When you’re targeting devices with more, shall we say, character (cough GPUs cough), it’s tempting to assume that anything strange you see is the result of some flaw in how they are doing arithmetic. But that is not necessarily the case; it could just be that your intuitive notion of what the result should be… is wrong.

If you’re going to do anything remotely edgy with floating-point – and certainly, quality benchmarking falls into that category – you’d better get used to thinking about exactly what’s happening inside the floating-point unit, which means understanding how floating-point works in a lot more detail than, perhaps, you really wanted to. Get over it, hacker!

Read on at MALI central