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.

41

3D-Tech News Around The Web / Intel Introducing the OpenCL 2013 SDK

« on: March 30, 2013, 04:43:01 PM »

Introducing the OpenCL 2013 SDK
Develop in a comprehensive environment for OpenCL applications

The Intel SDK for OpenCL* Applications 2013 is a software development environment for OpenCL* applications on 3rd and future 4th Generations Intel® Core™ Processors for Windows* 7 and Windows* 8 operating systems.

The New Intel SDK for OpenCL* Applications 2013 extends Intel’s support of open standards to include certified OpenCL* 1.2 support for both 3rd and future 4th Generation Intel® Core™ Processors on both the Intel® CPU and Intel HD Graphics.

42

3D-Tech News Around The Web / (Android) Mobile GPUMark V2

« on: March 30, 2013, 04:11:23 PM »

This benchmark software measures the 3D capabilities of your smartphone or tablet.
In addition to the benchmark mode used to measure 3D capabilities, the software also comes equipped with a demo mode, which gives you real-time control over the 3D graphics used in the benchmark.

The 3D graphics of MOBILE GPUMARK use YEBIS 2’s post-processing effects.
Post-processing effects technology is used to create photorealistic CG images, and is an essential element of cutting-edge 3D game graphics.
However, at the present time (2012), it is rarely used in real-time 3D content for smartphones and tablets because of processing speed issues.

MOBILE GPUMARK is a cutting-edge mobile application featuring the post-effect techniques used in top-of-the-line 3D graphics.
Now, you can enjoy a rich 3D experience hitherto considered impossible on your mobile device.

- Changed the calculation of the scores. Note that the calculation is greatly changed from the previous version (1.0).
The ranking is computed differently in version 1.0 and 2.0.
(You may browse the scores calculated by both versions with a web browser.)
- Optimized application launch time by downloading demo assets on the first execution.
- Fixed demos took a long time to be launched on some devices.
- Fixed noise on BENCHMARK mode on some devices.

If you can live with bad english and an obscure score list, this the best looking benchmark for Android.
"Fixed noise" refers to graphical glitches seen with Adreno before.

43

3D-Tech News Around The Web / Beneath - semi-auto texturing tech demo

« on: March 30, 2013, 04:01:10 PM »

We built the Beneath demo for two reasons:

    We love building cool stuff
    To demonstrate the parametric fire power!


Substance Designer was used for all the texture assets of the scene, and allowed us to do "semi-auto texturing": texture your object once, reapply the process on as many objects as you want, saving up to 80% of production time.
How does this work?
This is the beauty of parametric texturing: because the low-poly mesh and possibly tangent space normal map are inputs of the substance file, the output maps you have defined once in this file (most probably, and at least, diffuse, normal, specular, etc.) will automatically adapt to the new geometry and UVs after asking Substance to do so.

Finally an executable demo again after all those videos.
Allegorithmic is also the author of the Android Windmill benchmark.

44

3D-Tech News Around The Web / Activision R&D Real-time Character Demo video

« on: March 29, 2013, 01:17:56 PM »

Activision R&D Real-time Character Demo

This animated character is being rendered in real-time on current video card hardware, using standard bone animation. The rendering techniques, as well as the animation pipeline are being presented at GDC 2013, "Next Generation Character Rendering" on March 27.
The original high resolution data was acquired from Light Stage Facial Scanning and Performance Capture by USC Institute for Creative Technologies, then converted to a 70 bones rig, while preserving the high frequency detail in diffuse, normal and displacement composite maps.
It is being rendered in a DirectX11 environment, using advanced techniques to faithfully represent the character's skin and eyes.

You can find more detail on the rendering aspect here : http://www.iryoku.com/blog

This demo is running at 180 fps on current gtx 680 cards.

Note: Yes, this is the same source data from ICT used by Nvidia at GTC, but rendered using a completely different tech.

45

3D-Tech News Around The Web / Re: (Android) Unigine releases Oil Rush 3D for Qualcomm’s Snapdragon S4

« on: March 27, 2013, 08:17:10 PM »

you would need
7-zip or alternative
Android SDK
APKTOOL
ZIPsigner  or alternative

besides the manifest you need to check any other relevant file in the APK if ATI texture compression is actually used or not.

46

3D-Tech News Around The Web / AMD Catalyst™ 13.3 Beta 3 for Linux

« on: March 24, 2013, 05:33:17 PM »

Feature Highlights of the AMD Catalyst™ 13.2 Beta Driver for Linux

Resolved Issues

    [370253]:  Serious Sam 3 - Color of Objects turning into be red when enabling separate shader object
    [371937]:  Team Fortress 2 - Screen black issue while entering the game screen under cinnamon desktop environment
    [371733]:  Team Fortress 2 - Change settings without restarting would reduce FPS down to the 20s/30s
    [371374]:  Team Fortress 2 - Screen random flickering and corruptions in Lakeside Map
    [369893]:  Xserver starting failure after switching to Power-Saving mode on PowerXpress A+I platform with Ubuntu 12.10
    [368970]:  System cannot switch to Power-Saving mode on some HP PowerXpress A+I platforms
    [370067]:  System hang up when logging out in Power-Saving mode on PowerXpress A+A platform
    [371116]:  Startx failure in Power-Saving mode on PowerXpress A+I platform
    [370316]:  Xserver crash in High-Performance mode on PowerXpress A+I platform with Intel Haswell
    [373156]:  Login screen garbage on PowerXpress A+I system with latest Intel graphics driver
    [372650]:  Black window issue for OpenGL applications when using XRender backend of kwin
    [369981]:  Adding Kernel 3.7 support
    [369982]:  Adding Kernel 3.8 support

47

3D-Tech News Around The Web / Re: NVIDIA CUDA on ARM glass demo

« on: March 24, 2013, 05:30:12 PM »

bump: added actual infos where the video belongs to

48

3D-Tech News Around The Web / NVIDIA VMware vSphere ESXi 5.1 Driver 304.76

« on: March 24, 2013, 03:14:46 PM »

New in Release 304.76:

This driver enables VMware's vSGA shared GPU capabilities.
Hardware based graphics acceleration for 3D workloads for VMware Horizon View virtual desktops or vSphere virtual machines.

    Supports VMware Horizon View 5.2 or later
    Requires all virtual machines to be at least VMware HWv9 compatible

49

3D-Tech News Around The Web / Re: AMD Catalyst™ 13.3 Beta 2 Driver

« on: March 20, 2013, 09:17:32 PM »

Feature Highlights of the AMD Catalyst™ 13.3 Beta3 Driver for Windows®

    Resolves OpenGL application issues seen with the AMD Catalyst 13.3 Beta2 driver

This "update" removes the new extensions.
You can thank the developer here:
https://twitter.com/CatalystCreator/status/314115029412765697


You can still uses this old workaround (with newer versions)
How to run OpenGL programs broken by ATI Catalyst 7.12+

50

3D-Tech News Around The Web / Kishonti CLBenchmark 1.1.3 released

« on: March 19, 2013, 06:55:20 PM »

The updated version of Kishonti Informatics' benchmark for OpenCL implementations is now available for download at www.clbenchmark.com.

Kishonti Informatics released the latest version of CLBenchmark Desktop Edition for consumers. CLBenchmark 1.1.3 includes bugfixes that solve usability issues in cases when the display resolution is lower than full HD resolutions.

Major new features

    Optical Flow: conformance issues fixed, improved compatibiliy
    Fixed visuals for down to 1366x768 display resolution

51

3D-Tech News Around The Web / AMD "Graphics Core Next" 25 Performance Tips

« on: March 19, 2013, 06:40:45 PM »

GCN's 25 Performance Tips from Nick Thibieroz
Nicolas Thibieroz from AMD has been posting a daily series of "Performance Tips" through his Twitter account.

These performance tips refer to the GCN architecture, which stands for "Graphics Core Next" that can be found in the ATI Radeon HD 7000 series.

52

3D-Tech News Around The Web / TechPowerUp GPU-Z v0.6.9

« on: March 19, 2013, 06:26:07 PM »

TechPowerUp GPU-Z v0.6.9

GPU-Z is a lightweight utility designed to give you all information about your video card and GPU.

Revision History
0.6.9

    Fixed shader count on AMD Radeon HD 7790
    Added support for AMD Radeon HD 8870M
    Added support for NVIDIA GeForce GTX 650 Ti Boost, GT 415, GT 750M
    Changed NVIDIA Kepler DirectX support to 11.0
    Fixed OpenCL detection showing double error message
    Added tooltips for GPU vendor logo, save bios, render test, screenshot button

53

3D-Tech News Around The Web / (Android) Unigine releases Oil Rush 3D for Qualcomm’s Snapdragon S4

« on: March 19, 2013, 06:17:45 PM »

A spectacular new mobile experience with Oil Rush 3D strategy game on your Android device

Oil Rush, an epic naval strategy game, is released for Android devices based on Qualcomm’s Snapdragon S4 chip. The game is already available on the Google Play Store and you can jump into the next-generation of 3D graphics, hardcore depth and touch-native controls directly on a mobile device. Oil Rush for Android is based on the proprietary multi-platform UNIGINE Engine and developed by UNIGINE Corp. Read more in the official press-release.

AndroidManifest.xml checks for GL_AMD_compressed_ATC_texture to make it Snapdragon exclusive.

54

3D-Tech News Around The Web / NVIDIA Encode SDK 2.0 with 3rd generation Kepler GK208 support

« on: March 19, 2013, 06:00:44 PM »

"This is Release 2.0 of NV Encode SDK.  This SDK release is provided "as is" for evaluation purposes, without any guarantees of backward  compatibiilty with future NVIDIA drivers.

Applications or source projects that use the NVIDIA NVENC Video Encoder API require:
* NVIDIA driver version 310.xx or newer
* NVIDIA GPU based on the Kepler Architecture (GK104 or higher)
    Quadro K4000 and higher
    GRID K340 and K520
    GRID K1 and K2
    Tesla K10 and K20
  Note: GeForce is not supported with the NVENC SDK"

NVENC SDK 2.0 incl. driver 312.07

NVENC API Reference Manual

NVENC Programming Guide

NVENC App Note


Graphics driver 312.07 64 bit exposes third generation Kepler GK208 and pretty much any other unreleased GPU

Code: [Select]

DriverVer   = 02/25/2013, 9.18.13.1207
...
NVIDIA_DEV.0F00 = "NVIDIA GeForce GT 630"
NVIDIA_DEV.0F01 = "NVIDIA GeForce GT 620"
NVIDIA_DEV.0FC0 = "NVIDIA GeForce GT 640"
NVIDIA_DEV.0FC1 = "NVIDIA GeForce GT 640 "
NVIDIA_DEV.0FC2 = "NVIDIA GeForce GT 630 "
NVIDIA_DEV.0FC4 = "NVIDIA D14P1-15"
NVIDIA_DEV.0FC5 = "NVIDIA D15M2-03"
NVIDIA_DEV.0FC6 = "NVIDIA GeForce GTX 650"
NVIDIA_DEV.0FD0 = "NVIDIA NB1G"
NVIDIA_DEV.0FD1 = "NVIDIA GeForce GT 650M"
NVIDIA_DEV.0FD2 = "NVIDIA GeForce GT 640M"
NVIDIA_DEV.0FD3 = "NVIDIA GeForce GT 640M LE"
NVIDIA_DEV.0FD8 = "NVIDIA GeForce GT 640M "
NVIDIA_DEV.0FD9 = "NVIDIA GeForce GT 645M"
NVIDIA_DEV.0FDA = "NVIDIA GK107-ES-A1"
NVIDIA_DEV.0FDB = "NVIDIA GK107-ESP-A1"
NVIDIA_DEV.0FDC = "NVIDIA GK107-INT22-A1"
NVIDIA_DEV.0FE0 = "NVIDIA GeForce GTX 660M"
NVIDIA_DEV.0FE1 = "NVIDIA GeForce GT 730M"
NVIDIA_DEV.0FE3 = "NVIDIA GeForce GT 745M"
NVIDIA_DEV.0FE4 = "NVIDIA GeForce GT 750M"
NVIDIA_DEV.0FE5 = "NVIDIA GeForce K340 USM"
NVIDIA_DEV.0FE6 = "NVIDIA NVS K1 USM"
NVIDIA_DEV.0FE7 = "NVIDIA Generic K1 USM"
NVIDIA_DEV.0FEF = "NVIDIA GRID K340"
NVIDIA_DEV.0FF0 = "NVIDIA NB1Q"
NVIDIA_DEV.0FF1 = "NVIDIA NVS 1000"
NVIDIA_DEV.0FF2 = "NVIDIA GRID K1"
NVIDIA_DEV.0FF5 = "NVIDIA Tesla K1 USM"
NVIDIA_DEV.0FF7 = "NVIDIA Quadro K1 USM"
NVIDIA_DEV.0FF9 = "NVIDIA Quadro K2000D"
NVIDIA_DEV.0FFA = "NVIDIA Quadro K600"
NVIDIA_DEV.0FFB = "NVIDIA Quadro K2000M"
NVIDIA_DEV.0FFC = "NVIDIA Quadro K1000M"
NVIDIA_DEV.0FFD = "NVIDIA NVS 510"
NVIDIA_DEV.0FFE = "NVIDIA Quadro K2000"
NVIDIA_DEV.0FFF = "NVIDIA Quadro 410"
NVIDIA_DEV.1001 = "NVIDIA D15U-60"
NVIDIA_DEV.1003 = "NVIDIA GK110 DT Bringup"
NVIDIA_DEV.1004 = "NVIDIA D15U-50"
NVIDIA_DEV.1005 = "NVIDIA GeForce GTX TITAN"
NVIDIA_DEV.101F = "NVIDIA Tesla K20"
NVIDIA_DEV.1020 = "NVIDIA Tesla K20X"
NVIDIA_DEV.1021 = "NVIDIA Tesla K20Xm"
NVIDIA_DEV.1022 = "NVIDIA Tesla K20c"
NVIDIA_DEV.1026 = "NVIDIA Tesla K20s"
NVIDIA_DEV.1028 = "NVIDIA Tesla K20m"
NVIDIA_DEV.103A = "NVIDIA Q13U-3"
NVIDIA_DEV.103B = "NVIDIA Q12U-1"
NVIDIA_DEV.1040 = "NVIDIA GeForce GT 520 "
NVIDIA_DEV.1041 = "NVIDIA D13M1-45"
NVIDIA_DEV.1042 = "NVIDIA GeForce 510"
NVIDIA_DEV.1048 = "NVIDIA GeForce 605"
NVIDIA_DEV.1049 = "NVIDIA GeForce GT 620 "
NVIDIA_DEV.104A = "NVIDIA GeForce GT 610"
NVIDIA_DEV.104B = "NVIDIA GeForce GT 625 (OEM)"
NVIDIA_DEV.1050 = "NVIDIA GeForce GT 520M"
NVIDIA_DEV.1054 = "NVIDIA GeForce 410M"
NVIDIA_DEV.1058 = "NVIDIA GeForce 610M "
NVIDIA_DEV.105A = "NVIDIA GeForce 610M  "
NVIDIA_DEV.105B = "NVIDIA GeForce 705M"
NVIDIA_DEV.107C = "NVIDIA NVS 315"
NVIDIA_DEV.107D = "NVIDIA NVS 310"
NVIDIA_DEV.107E = "NVIDIA GF119-INT"
NVIDIA_DEV.107F = "NVIDIA GF119-ES"
NVIDIA_DEV.1080 = "NVIDIA GeForce GTX 580"
NVIDIA_DEV.1081 = "NVIDIA GeForce GTX 570"
NVIDIA_DEV.1082 = "NVIDIA GeForce GTX 560 Ti"
NVIDIA_DEV.1084 = "NVIDIA GeForce GTX 560"
NVIDIA_DEV.1086 = "NVIDIA GeForce GTX 570 "
NVIDIA_DEV.1087 = "NVIDIA GeForce GTX 560 Ti "
NVIDIA_DEV.1088 = "NVIDIA GeForce GTX 590"
NVIDIA_DEV.1089 = "NVIDIA GeForce GTX 580 "
NVIDIA_DEV.108B = "NVIDIA GeForce GTX 580  "
NVIDIA_DEV.108C = "NVIDIA D13U"
NVIDIA_DEV.108E = "NVIDIA Tesla C2090"
NVIDIA_DEV.1091 = "NVIDIA Tesla M2090"
NVIDIA_DEV.1091.0887.10DE = "NVIDIA Tesla M2090 "
NVIDIA_DEV.1091.088E.10DE = "NVIDIA Tesla X2090"
NVIDIA_DEV.1091.0891.10DE = "NVIDIA Tesla X2090 "
NVIDIA_DEV.1094 = "NVIDIA Tesla M2075"
NVIDIA_DEV.1094.0888.10DE = "NVIDIA Tesla M2075 "
NVIDIA_DEV.1096 = "NVIDIA Tesla C2075"
NVIDIA_DEV.1096.0910.10DE = "NVIDIA Tesla C2075 "
NVIDIA_DEV.1096.0911.10DE = "NVIDIA Tesla C2050 "
NVIDIA_DEV.1098 = "NVIDIA D13U "
NVIDIA_DEV.109A = "NVIDIA Quadro 5010M"
NVIDIA_DEV.109B = "NVIDIA Quadro 7000"
NVIDIA_DEV.109B.0918.10DE = "NVIDIA Quadro 7000 "
NVIDIA_DEV.10C0 = "NVIDIA GeForce 9300 GS "
NVIDIA_DEV.10C3 = "NVIDIA GeForce 8400GS"
NVIDIA_DEV.10C4 = "NVIDIA ION   "
NVIDIA_DEV.10C5 = "NVIDIA GeForce 405  "
NVIDIA_DEV.10D8 = "NVIDIA NVS 300"
NVIDIA_DEV.1140 = "NVIDIA GF117"
NVIDIA_DEV.1180 = "NVIDIA GeForce GTX 680"
NVIDIA_DEV.1182 = "NVIDIA GK104"
NVIDIA_DEV.1183 = "NVIDIA GeForce GTX 660 Ti"
NVIDIA_DEV.1184 = "NVIDIA GK104 "
NVIDIA_DEV.1185 = "NVIDIA GeForce GTX 660"
NVIDIA_DEV.1187 = "NVIDIA GK104  "
NVIDIA_DEV.1188 = "NVIDIA GeForce GTX 690"
NVIDIA_DEV.1189 = "NVIDIA GeForce GTX 670"
NVIDIA_DEV.118A = "NVIDIA GRID K520"
NVIDIA_DEV.118B = "NVIDIA GeForce K2 USM"
NVIDIA_DEV.118C = "NVIDIA NVS K2 USM"
NVIDIA_DEV.118D = "NVIDIA Generic K2 USM"
NVIDIA_DEV.118F = "NVIDIA Tesla K10"
NVIDIA_DEV.1192 = "NVIDIA GeForce GK104"
NVIDIA_DEV.119F = "NVIDIA GeForce GTX 780M"
NVIDIA_DEV.11A0 = "NVIDIA GeForce GTX 680M"
NVIDIA_DEV.11A1 = "NVIDIA GeForce GTX 670MX"
NVIDIA_DEV.11A7 = "NVIDIA GeForce GTX 675MX"
NVIDIA_DEV.11AA = "NVIDIA GK104-INT"
NVIDIA_DEV.11B0 = "NVIDIA Quadro K2 USM"
NVIDIA_DEV.11B1 = "NVIDIA Tesla K2 USM"
NVIDIA_DEV.11B6 = "NVIDIA N15E-Q1"
NVIDIA_DEV.11B7 = "NVIDIA N15E-Q3"
NVIDIA_DEV.11B8 = "NVIDIA N15E-Q5"
NVIDIA_DEV.11BA = "NVIDIA Quadro K5000"
NVIDIA_DEV.11BB = "NVIDIA Quadro 4100"
NVIDIA_DEV.11BC = "NVIDIA Quadro K5000M"
NVIDIA_DEV.11BD = "NVIDIA Quadro K4000M"
NVIDIA_DEV.11BE = "NVIDIA Quadro K3000M"
NVIDIA_DEV.11BF = "NVIDIA GRID K2"
NVIDIA_DEV.11C0 = "NVIDIA GeForce GTX 660 "
NVIDIA_DEV.11C1 = "NVIDIA D14P2-30"
NVIDIA_DEV.11C2 = "NVIDIA GK106"
NVIDIA_DEV.11C3 = "NVIDIA GeForce GTX 650 Ti"
NVIDIA_DEV.11C4 = "NVIDIA GeForce GTX 645"
NVIDIA_DEV.11C6 = "NVIDIA GeForce GTX 650 Ti "
NVIDIA_DEV.11D0 = "NVIDIA GK106-INT353"
NVIDIA_DEV.11D1 = "NVIDIA GK106-INT343"
NVIDIA_DEV.11D2 = "NVIDIA GK106-INT232"
NVIDIA_DEV.11D3 = "NVIDIA GK106-ES"
NVIDIA_DEV.11E2 = "NVIDIA GeForce GTX 765M"
NVIDIA_DEV.11E3 = "NVIDIA GeForce GTX 760M"
NVIDIA_DEV.11FA = "NVIDIA Quadro K4000"
NVIDIA_DEV.11FF = "NVIDIA NB1Q "
NVIDIA_DEV.1200 = "NVIDIA GeForce GTX 560 Ti  "
NVIDIA_DEV.1201 = "NVIDIA GeForce GTX 560 "
NVIDIA_DEV.1202 = "NVIDIA GeForce GTX 560 Ti   "
NVIDIA_DEV.1203 = "NVIDIA GeForce GTX 460 SE v2"
NVIDIA_DEV.1205 = "NVIDIA GeForce GTX 460 v2"
NVIDIA_DEV.1206 = "NVIDIA GeForce  GTX 555"
NVIDIA_DEV.1207 = "NVIDIA GeForce GT 645"
NVIDIA_DEV.1208 = "NVIDIA GeForce GTX 560 SE"
NVIDIA_DEV.1213 = "NVIDIA GeForce GTX 670M"
NVIDIA_DEV.121F = "NVIDIA GF114-INT"
NVIDIA_DEV.1240 = "NVIDIA D13P1-35"
NVIDIA_DEV.1241 = "NVIDIA GeForce GT 545"
NVIDIA_DEV.1243 = "NVIDIA GeForce GT 545 "
NVIDIA_DEV.1244 = "NVIDIA GeForce GTX 550 Ti"
NVIDIA_DEV.1245 = "NVIDIA GeForce GTS 450   "
NVIDIA_DEV.1249 = "NVIDIA GeForce GTS 450    "
NVIDIA_DEV.124B = "NVIDIA GeForce GT 640  "
NVIDIA_DEV.1250 = "NVIDIA GF116-INT"
NVIDIA_DEV.1251 = "NVIDIA GeForce GTX 560M"
NVIDIA_DEV.1280 = "NVIDIA GeForce GT 635"
NVIDIA_DEV.1281 = "NVIDIA D15M2-05"
NVIDIA_DEV.1282 = "NVIDIA D15M2-20"
NVIDIA_DEV.1283 = "NVIDIA D15M2-10"
NVIDIA_DEV.1285 = "NVIDIA GK208-100"
NVIDIA_DEV.1290 = "NVIDIA GeForce GT 730M "
NVIDIA_DEV.1291 = "NVIDIA GeForce GT 735M"
NVIDIA_DEV.1292 = "NVIDIA GeForce GT 740M"
NVIDIA_DEV.1293 = "NVIDIA GeForce GT 730M  "
NVIDIA_DEV.1294 = "NVIDIA GeForce GT 740M "
NVIDIA_DEV.12A0 = "NVIDIA GK208"
NVIDIA_DEV.12AD = "NVIDIA GK208-ES"
NVIDIA_DEV.12AE = "NVIDIA GK208-CS1-C"
NVIDIA_DEV.12AF = "NVIDIA GK208-INT"
NVIDIA_DEV.12B0 = "NVIDIA GK208-CS-Q"
NVIDIA_DEV.12B1 = "NVIDIA GK208 INT"


55

3D-Tech News Around The Web / NVIDIA CUDA 5.0 for MAC release 5.0.45

« on: March 16, 2013, 08:35:35 AM »

New in Release 5.0.45

    Support for MacOS 10.8.3

I have no Mac for testing, so i took a look which Maxwell functions libgpgpucomp.dylib contains meanwhile

_GetMaxSharedMemory_maxwell _GetMaxLocalMemory_maxwell _GetConstantBankSize_maxwell _GetMaxTexturesPerEntry_maxwell _GetMaxSamplersPerEntry_maxwell _GetMaxSurfacesPerEntry_maxwell _GetParamConstBank_maxwell _GetParamConstBase_maxwell _GetMaxParamConstSize_maxwell _GetParamSharedBase_maxwell _GetMaxParamSharedSize_maxwell _GetEnvregConstBank_maxwell _GetOCGConstBank_maxwell _GetDriverConstantBank_maxwell _GetGlobalRelocConstBank_maxwell _GetConstBackingStoreBank_maxwell _GetIsUserConstBank_maxwell _GetIsGlobalConstBank_maxwell _GetEnvregConstBase_maxwell _GetConstBackingStoreBase_maxwell _GetUsesBindlessFormat_maxwell _GetBindlessTextureBank_maxwell _GetBindlessSurfaceBank_maxwell _GetUsesLayeredSurfaceEmulation_maxwell _GetIsQueryDescBank_maxwell _GetTextureQueryDescriptorStorage_maxwell _GetGlobalQueryDescTableBank_maxwell _GetGlobalTextureQueryDescTableBase_maxwell _GetGlobalSamplerQueryDescTableBase_maxwell _GetBindlessTextureImmediateOffset_maxwell _GetBindlessSurfaceHeaderSize_maxwell _GetBindlessTextureHeaderIndexSize_maxwell _GetUsesIndirectionForGlobals_maxwell _GetGlobalMemorySegment_maxwell _GetConstPointerKind_maxwell _GetPTXCbankForHWCbank_maxwell  _GetTextureQueryDescriptorStorage_fermi _GetSurfaceQueryDescriptorStorage_tesla _GetHWStorageForPtxCbank_maxwell _GetSurfaceQueryDescriptorStorage_maxwell _GetHWStorageForPtxCbank_kepler _GetHWStorageForPtxCbank_fermi _GetSurfaceQueryDescriptorStorage_kepler _GetIsLocalConstBank_kepler _GetIsLocalConstBank_maxwell _GetIsLocalConstBank_fermi _GetIsLocalConstBank_tesla

56

3D-Tech News Around The Web / NVIDIA Geforce/Verde driver 314.21

« on: March 16, 2013, 08:07:06 AM »

   
Lara Croft Joins GeForce with 45% Performance Gain

Release Summary

    Improves performance and stability in Tomb Raider
    Adds new SLI and 3D Vision profiles.

57

3D-Tech News Around The Web / AMD Catalyst™ 13.3 Beta 2 Driver

« on: March 15, 2013, 10:47:01 PM »

Feature Highlights of the AMD Catalyst™ 13.3 Beta Driver for Windows®

    Improve performance in Sim City 5 up to 16 percent
    Improves performance in Far Cry 3 up to 5 percent
    Improves latency performance issues seen in Tomb Raider and Hitman Absolution
    Resolves slight corruption seen in Tomb Raider with TressFX enabled for CrossFire and single GPU configurations

also 9 new OpenGL extensions, mostly OpenGL 4.3

58

3D-Tech News Around The Web / (Android) OpenCL info for Qualcomm Snapdragon S4

« on: March 15, 2013, 04:57:30 PM »

Made progress in Nexus 4 phone for using OpenCL in java & also made it to work with aparapi framework , so one can write pure java applications (using GPGPU & OpenCL) on the Nexus 4 devices. IMHO same approach can be used for any other future Android phones with proper OpenCL.so libraries deployed in the phones (without HW/SW vendor's SDKs).

Please find code at google-code

Source: Qualcomm

Code: [Select]

I/ActivityManager(471): START u0 {act=android.intent.action.MAIN cat=[android.intent.category.LAUNCHER] flg=0x10200000 cmp=org.aopencl.clinfo/.MainActivity} from pid 965
I/ActivityManager(471): Start proc org.aopencl.clinfo for activity org.aopencl.clinfo/.MainActivity: pid=3007 uid=10127 gids={50127, 1028}
D/libEGL(3007): loaded /system/lib/egl/libEGL_adreno200.so
I/CLInfo(3007): CLInfo:QUALCOMM Snapdragon(TM)
I/CLInfo(3007): 0:QUALCOMM Adreno(TM)
I/CLInfo(3007):  Max Compute Units: 4
I/CLInfo(3007):   Max work group size: 256
I/CLInfo(3007):  Max Work Item Dimensions: 3
I/CLInfo(3007):   Max work item dimensions: 3
I/CLInfo(3007):     Max work items: (256,256,256)
I/CLInfo(3007):   Preferred vector width char: 1
I/CLInfo(3007):   Preferred vector width short: 1
I/CLInfo(3007):   Preferred vector width int: 1
I/CLInfo(3007):   Preferred vector width long: 1
I/CLInfo(3007):   Preferred vector width float: 1
I/CLInfo(3007):   Preferred vector width double: 0
I/CLInfo(3007):   Max clock frequency: 325MHz
I/CLInfo(3007):   Address bits: 32bits
I/CLInfo(3007):   Max memory allocation: 981811200 bytes
I/CLInfo(3007):   Image support: True
I/CLInfo(3007):   Max size of kernel argument: 256
I/CLInfo(3007):   Alignment of base addres: 512 bits
I/CLInfo(3007):   Minimum alignment for any datatype: 64 bytes
I/CLInfo(3007):     Denorms: False
I/CLInfo(3007):     Quiet NaNs: False
I/CLInfo(3007):     Round to nearest even: False
I/CLInfo(3007):     Round to zero: False
I/CLInfo(3007):     Round to +ve and infinity: False
I/CLInfo(3007):     IEEE754-2008 fused multiply-add: False
I/CLInfo(3007): Cache type err:0
I/CLInfo(3007):   Cache line size: 16 bytes
I/CLInfo(3007):   Cache size: 32768 bytes
I/CLInfo(3007):   Global memory size: 1963622400 bytes
I/CLInfo(3007):   Constant buffer size: 4096 bytes
I/CLInfo(3007):   Max number of constant args: 8
I/CLInfo(3007):   Local memory type err:0
I/CLInfo(3007):   Local memory size: 8192 bytes
I/CLInfo(3007):   Profiling timer resolution: 1000
I/CLInfo(3007):   Device endianess: True
I/CLInfo(3007):   Available: True
I/CLInfo(3007):   Compiler available: False
I/CLInfo(3007):   Execution capabilities:
I/CLInfo(3007):   Execute OpenCL kernels: True
I/CLInfo(3007):   Execute native kernels: True
I/CLInfo(3007):   Queue properties:
I/CLInfo(3007):    Out-of-Order: False
I/CLInfo(3007):     Profiling: False
I/CLInfo(3007):   Name: QUALCOMM Adreno(TM)
I/CLInfo(3007):   Vendor: QUALCOMM
I/CLInfo(3007): Error:CL_DRIVER_VERSION:-30
I/CLInfo(3007):   Profile: EMBEDDED_PROFILE
I/CLInfo(3007):   Version: OpenCL 1.1 Adreno(TM) 320
I/CLInfo(3007):   Extensions: cl_khr_byte_addressable_store cl_khr_fp16 cl_khr_gl_sharing cl_khr_global_int32_base_atomics cl_khr_global_int32_extended_atomics cl_khr_local_int32_base_atomics cl_khr_local_int32_extended_atomics cl_qcom_default_relaxed_math cl_qcom_perf_monitor
I/CLInfo(3007): 1:QUALCOMM Krait(TM)
I/CLInfo(3007):  Max Compute Units: 4
I/CLInfo(3007):   Max work group size: 1
I/CLInfo(3007):  Max Work Item Dimensions: 3
I/CLInfo(3007):   Max work item dimensions: 3
I/CLInfo(3007):     Max work items: (1,1,1)
I/CLInfo(3007):   Preferred vector width char: 16
I/CLInfo(3007):   Preferred vector width short: 16
I/CLInfo(3007):   Preferred vector width int: 16
I/CLInfo(3007):   Preferred vector width long: 1
I/CLInfo(3007):   Preferred vector width float: 16
I/CLInfo(3007):   Preferred vector width double: 0
I/CLInfo(3007):   Max clock frequency: 1500MHz
I/CLInfo(3007):   Address bits: 32bits
I/CLInfo(3007):   Max memory allocation: 981811200 bytes
I/CLInfo(3007):   Image support: True
I/CLInfo(3007):   Max size of kernel argument: 256
I/CLInfo(3007):   Alignment of base addres: 1024 bits
I/CLInfo(3007):   Minimum alignment for any datatype: 128 bytes
I/CLInfo(3007):     Denorms: False
I/CLInfo(3007):     Quiet NaNs: False
I/CLInfo(3007):     Round to nearest even: False
I/CLInfo(3007):     Round to zero: False
I/CLInfo(3007):     Round to +ve and infinity: False
I/CLInfo(3007):     IEEE754-2008 fused multiply-add: False
I/CLInfo(3007): Cache type err:0
I/CLInfo(3007):   Cache line size: 64 bytes
I/CLInfo(3007):   Cache size: 1048576 bytes
I/CLInfo(3007):   Global memory size: 981811200 bytes
I/CLInfo(3007):   Constant buffer size: 65536 bytes
I/CLInfo(3007):   Max number of constant args: 8
I/CLInfo(3007):   Local memory type err:0
I/CLInfo(3007):   Local memory size: 32768 bytes
I/CLInfo(3007):   Profiling timer resolution: 0
I/CLInfo(3007):   Device endianess: True
I/CLInfo(3007):   Available: True
I/CLInfo(3007):   Compiler available: True
I/CLInfo(3007):   Execution capabilities:
I/CLInfo(3007):   Execute OpenCL kernels: False
I/CLInfo(3007):   Execute native kernels: False
I/CLInfo(3007):   Queue properties:
I/CLInfo(3007):    Out-of-Order: False
I/CLInfo(3007):     Profiling: False
I/CLInfo(3007):   Name: QUALCOMM Krait(TM)
I/CLInfo(3007):   Vendor: QUALCOMM
I/CLInfo(3007): Error:CL_DRIVER_VERSION:-30
I/CLInfo(3007):   Profile: EMBEDDED_PROFILE
I/CLInfo(3007):   Version: OpenCL 1.1 Krait(TM)
I/CLInfo(3007):   Extensions: cl_khr_global_int32_base_atomics cl_khr_global_int32_extended_atomics cl_khr_local_int32_base_atomics cl_khr_local_int32_extended_atomics cl_khr_byte_addressable_store cles_khr_int64 cl_khr_fp16
D/libEGL(3007): loaded /system/lib/egl/libGLESv1_CM_adreno200.so
D/libEGL(3007): loaded /system/lib/egl/libGLESv2_adreno200.so
I/Adreno200-EGL(3007): <eglInitialize:269>: EGL 1.4 QUALCOMM build: Nondeterministic AU_full_mako_PARTNER-ANDROID/JB-MR1-DEV_CL2961380_release_AU (CL2961380)
I/Adreno200-EGL(3007): Build Date: 12/10/12 Mon
I/Adreno200-EGL(3007): Local Branch:
I/Adreno200-EGL(3007): Remote Branch: m/partner-android/jb-mr1-dev
I/Adreno200-EGL(3007): Local Patches: NONE
I/Adreno200-EGL(3007): Reconstruct Branch: NOTHING
D/OpenGLRenderer(3007): Enabling debug mode 0
I/ActivityManager(471): Displayed org.aopencl.clinfo/.MainActivity: +478ms


59

3D-Tech News Around The Web / Maximizing PhysX-based particle effects in Planetside 2

« on: March 14, 2013, 04:15:06 AM »

The purpose of this article is to discuss how to incorporate GPU accelerated effects into a project without negatively impacting the overall performance and framerate of a game.


The key to making this work is to run all visual effects independently of the main game thread and rendering pipeline.  While the concept is simple, as always, the devil is in the details and there are a lot of things to consider to make this work properly.

60

3D-Tech News Around The Web / NVIDIA CUDA on ARM glass demo

« on: March 13, 2013, 06:33:26 PM »

Kayla Platform
ARM Development Platform for CUDA® and OpenGL

Introducing the Kayla Platform for computing on the ARM architecture – where supercomputing meets mobile computing.

The Kayla platform is powered by an NVIDIA® Tegra® Quad-core ARM processor and a Kepler™ GPU to deliver the highest performance, highest efficiency for the next generation of CUDA and OpenGL application. Pre-installed with CUDA 5 and supporting OpenGL 4.3, it provides ARM applications development across the widest range of application types.

download video demo here