Show Posts

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.


Topics - Stefan

Pages: 1 ... 103 104 [105] 106 107 ... 162
2081
Quote
Woody3D™ is a Tree Engine™ that generates 3D trees for real-time rendering. Dynamic libraries (x86, x64) for Windows and OSX operating systems are included. Trees are animated using the CPU or with the GPU using the included vertex shaders (GLSL / HLSL).


2082
Quote
CUDA Toolkit 3.2 (November 2010) Release Highlights

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



NVIDIA's oclDeviceQuery yet ignores multiple OpenCL vendors

Code: [Select]
oclDeviceQuery.exe Starting...

OpenCL SW Info:

 CL_PLATFORM_NAME: NVIDIA CUDA
 CL_PLATFORM_VERSION: OpenCL 1.0 CUDA 3.2.1
 OpenCL SDK Revision: 7027912


OpenCL Device Info:

 1 devices found supporting OpenCL:

 ---------------------------------
 Device GeForce GTX 465
 ---------------------------------
  CL_DEVICE_NAME: GeForce GTX 465
  CL_DEVICE_VENDOR: NVIDIA Corporation
  CL_DRIVER_VERSION: 263.06
  CL_DEVICE_VERSION: OpenCL 1.0 CUDA
  CL_DEVICE_TYPE: CL_DEVICE_TYPE_GPU
  CL_DEVICE_MAX_COMPUTE_UNITS: 11
  CL_DEVICE_MAX_WORK_ITEM_DIMENSIONS: 3
  CL_DEVICE_MAX_WORK_ITEM_SIZES: 1024 / 1024 / 64
  CL_DEVICE_MAX_WORK_GROUP_SIZE: 1024
  CL_DEVICE_MAX_CLOCK_FREQUENCY: 810 MHz
  CL_DEVICE_ADDRESS_BITS: 32
  CL_DEVICE_MAX_MEM_ALLOC_SIZE: 248 MByte
  CL_DEVICE_GLOBAL_MEM_SIZE: 993 MByte
  CL_DEVICE_ERROR_CORRECTION_SUPPORT: no
  CL_DEVICE_LOCAL_MEM_TYPE: local
  CL_DEVICE_LOCAL_MEM_SIZE: 48 KByte
  CL_DEVICE_MAX_CONSTANT_BUFFER_SIZE: 64 KByte
  CL_DEVICE_QUEUE_PROPERTIES: CL_QUEUE_OUT_OF_ORDER_EXEC_MODE_ENABLE
  CL_DEVICE_QUEUE_PROPERTIES: CL_QUEUE_PROFILING_ENABLE
  CL_DEVICE_IMAGE_SUPPORT: 1
  CL_DEVICE_MAX_READ_IMAGE_ARGS: 128
  CL_DEVICE_MAX_WRITE_IMAGE_ARGS: 8
  CL_DEVICE_SINGLE_FP_CONFIG: denorms INF-quietNaNs round-to-nearest round-to-zero round-to-inf fma

  CL_DEVICE_IMAGE <dim> 2D_MAX_WIDTH 4096
2D_MAX_HEIGHT 32768
3D_MAX_WIDTH 2048
3D_MAX_HEIGHT 2048
3D_MAX_DEPTH 2048

  CL_DEVICE_EXTENSIONS: cl_khr_byte_addressable_store
cl_khr_icd
cl_khr_gl_sharing
cl_nv_d3d9_sharing
cl_nv_d3d10_sharing
cl_khr_d3d10_sharing
cl_nv_d3d11_sharing
cl_nv_compiler_options
cl_nv_device_attribute_query
cl_nv_pragma_unroll
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_fp64


  CL_DEVICE_COMPUTE_CAPABILITY_NV: 2.0
  NUMBER OF MULTIPROCESSORS: 11
  NUMBER OF CUDA CORES: 352
  CL_DEVICE_REGISTERS_PER_BLOCK_NV: 32768
  CL_DEVICE_WARP_SIZE_NV: 32
  CL_DEVICE_GPU_OVERLAP_NV: CL_TRUE
  CL_DEVICE_KERNEL_EXEC_TIMEOUT_NV: CL_TRUE
  CL_DEVICE_INTEGRATED_MEMORY_NV: CL_FALSE
  CL_DEVICE_PREFERRED_VECTOR_WIDTH_<t> CHAR 1, SHORT 1, INT 1, LONG 1, FLOAT 1, DOUBLE 1


  ---------------------------------
  2D Image Formats Supported (71)
  ---------------------------------
  #     Channel Order   Channel Type         

  1     CL_R            CL_FLOAT             
  2     CL_R            CL_HALF_FLOAT         
  3     CL_R            CL_UNORM_INT8         
  4     CL_R            CL_UNORM_INT16       
  5     CL_R            CL_SNORM_INT16       
  6     CL_R            CL_SIGNED_INT8       
  7     CL_R            CL_SIGNED_INT16       
  8     CL_R            CL_SIGNED_INT32       
  9     CL_R            CL_UNSIGNED_INT8     
  10    CL_R            CL_UNSIGNED_INT16     
  11    CL_R            CL_UNSIGNED_INT32     
  12    CL_A            CL_FLOAT             
  13    CL_A            CL_HALF_FLOAT         
  14    CL_A            CL_UNORM_INT8         
  15    CL_A            CL_UNORM_INT16       
  16    CL_A            CL_SNORM_INT16       
  17    CL_A            CL_SIGNED_INT8       
  18    CL_A            CL_SIGNED_INT16       
  19    CL_A            CL_SIGNED_INT32       
  20    CL_A            CL_UNSIGNED_INT8     
  21    CL_A            CL_UNSIGNED_INT16     
  22    CL_A            CL_UNSIGNED_INT32     
  23    CL_RG           CL_FLOAT             
  24    CL_RG           CL_HALF_FLOAT         
  25    CL_RG           CL_UNORM_INT8         
  26    CL_RG           CL_UNORM_INT16       
  27    CL_RG           CL_SNORM_INT16       
  28    CL_RG           CL_SIGNED_INT8       
  29    CL_RG           CL_SIGNED_INT16       
  30    CL_RG           CL_SIGNED_INT32       
  31    CL_RG           CL_UNSIGNED_INT8     
  32    CL_RG           CL_UNSIGNED_INT16     
  33    CL_RG           CL_UNSIGNED_INT32     
  34    CL_RA           CL_FLOAT             
  35    CL_RA           CL_HALF_FLOAT         
  36    CL_RA           CL_UNORM_INT8         
  37    CL_RA           CL_UNORM_INT16       
  38    CL_RA           CL_SNORM_INT16       
  39    CL_RA           CL_SIGNED_INT8       
  40    CL_RA           CL_SIGNED_INT16       
  41    CL_RA           CL_SIGNED_INT32       
  42    CL_RA           CL_UNSIGNED_INT8     
  43    CL_RA           CL_UNSIGNED_INT16     
  44    CL_RA           CL_UNSIGNED_INT32     
  45    CL_RGBA         CL_FLOAT             
  46    CL_RGBA         CL_HALF_FLOAT         
  47    CL_RGBA         CL_UNORM_INT8         
  48    CL_RGBA         CL_UNORM_INT16       
  49    CL_RGBA         CL_SNORM_INT16       
  50    CL_RGBA         CL_SIGNED_INT8       
  51    CL_RGBA         CL_SIGNED_INT16       
  52    CL_RGBA         CL_SIGNED_INT32       
  53    CL_RGBA         CL_UNSIGNED_INT8     
  54    CL_RGBA         CL_UNSIGNED_INT16     
  55    CL_RGBA         CL_UNSIGNED_INT32     
  56    CL_BGRA         CL_UNORM_INT8         
  57    CL_BGRA         CL_SIGNED_INT8       
  58    CL_BGRA         CL_UNSIGNED_INT8     
  59    CL_ARGB         CL_UNORM_INT8         
  60    CL_ARGB         CL_SIGNED_INT8       
  61    CL_ARGB         CL_UNSIGNED_INT8     
  62    CL_INTENSITY    CL_FLOAT             
  63    CL_INTENSITY    CL_HALF_FLOAT         
  64    CL_INTENSITY    CL_UNORM_INT8         
  65    CL_INTENSITY    CL_UNORM_INT16       
  66    CL_INTENSITY    CL_SNORM_INT16       
  67    CL_LUMINANCE    CL_FLOAT             
  68    CL_LUMINANCE    CL_HALF_FLOAT         
  69    CL_LUMINANCE    CL_UNORM_INT8         
  70    CL_LUMINANCE    CL_UNORM_INT16       
  71    CL_LUMINANCE    CL_SNORM_INT16       

  ---------------------------------
  3D Image Formats Supported (71)
  ---------------------------------
  #     Channel Order   Channel Type         

  1     CL_R            CL_FLOAT             
  2     CL_R            CL_HALF_FLOAT         
  3     CL_R            CL_UNORM_INT8         
  4     CL_R            CL_UNORM_INT16       
  5     CL_R            CL_SNORM_INT16       
  6     CL_R            CL_SIGNED_INT8       
  7     CL_R            CL_SIGNED_INT16       
  8     CL_R            CL_SIGNED_INT32       
  9     CL_R            CL_UNSIGNED_INT8     
  10    CL_R            CL_UNSIGNED_INT16     
  11    CL_R            CL_UNSIGNED_INT32     
  12    CL_A            CL_FLOAT             
  13    CL_A            CL_HALF_FLOAT         
  14    CL_A            CL_UNORM_INT8         
  15    CL_A            CL_UNORM_INT16       
  16    CL_A            CL_SNORM_INT16       
  17    CL_A            CL_SIGNED_INT8       
  18    CL_A            CL_SIGNED_INT16       
  19    CL_A            CL_SIGNED_INT32       
  20    CL_A            CL_UNSIGNED_INT8     
  21    CL_A            CL_UNSIGNED_INT16     
  22    CL_A            CL_UNSIGNED_INT32     
  23    CL_RG           CL_FLOAT             
  24    CL_RG           CL_HALF_FLOAT         
  25    CL_RG           CL_UNORM_INT8         
  26    CL_RG           CL_UNORM_INT16       
  27    CL_RG           CL_SNORM_INT16       
  28    CL_RG           CL_SIGNED_INT8       
  29    CL_RG           CL_SIGNED_INT16       
  30    CL_RG           CL_SIGNED_INT32       
  31    CL_RG           CL_UNSIGNED_INT8     
  32    CL_RG           CL_UNSIGNED_INT16     
  33    CL_RG           CL_UNSIGNED_INT32     
  34    CL_RA           CL_FLOAT             
  35    CL_RA           CL_HALF_FLOAT         
  36    CL_RA           CL_UNORM_INT8         
  37    CL_RA           CL_UNORM_INT16       
  38    CL_RA           CL_SNORM_INT16       
  39    CL_RA           CL_SIGNED_INT8       
  40    CL_RA           CL_SIGNED_INT16       
  41    CL_RA           CL_SIGNED_INT32       
  42    CL_RA           CL_UNSIGNED_INT8     
  43    CL_RA           CL_UNSIGNED_INT16     
  44    CL_RA           CL_UNSIGNED_INT32     
  45    CL_RGBA         CL_FLOAT             
  46    CL_RGBA         CL_HALF_FLOAT         
  47    CL_RGBA         CL_UNORM_INT8         
  48    CL_RGBA         CL_UNORM_INT16       
  49    CL_RGBA         CL_SNORM_INT16       
  50    CL_RGBA         CL_SIGNED_INT8       
  51    CL_RGBA         CL_SIGNED_INT16       
  52    CL_RGBA         CL_SIGNED_INT32       
  53    CL_RGBA         CL_UNSIGNED_INT8     
  54    CL_RGBA         CL_UNSIGNED_INT16     
  55    CL_RGBA         CL_UNSIGNED_INT32     
  56    CL_BGRA         CL_UNORM_INT8         
  57    CL_BGRA         CL_SIGNED_INT8       
  58    CL_BGRA         CL_UNSIGNED_INT8     
  59    CL_ARGB         CL_UNORM_INT8         
  60    CL_ARGB         CL_SIGNED_INT8       
  61    CL_ARGB         CL_UNSIGNED_INT8     
  62    CL_INTENSITY    CL_FLOAT             
  63    CL_INTENSITY    CL_HALF_FLOAT         
  64    CL_INTENSITY    CL_UNORM_INT8         
  65    CL_INTENSITY    CL_UNORM_INT16       
  66    CL_INTENSITY    CL_SNORM_INT16       
  67    CL_LUMINANCE    CL_FLOAT             
  68    CL_LUMINANCE    CL_HALF_FLOAT         
  69    CL_LUMINANCE    CL_UNORM_INT8         
  70    CL_LUMINANCE    CL_UNORM_INT16       
  71    CL_LUMINANCE    CL_SNORM_INT16       

oclDeviceQuery, Platform Name = NVIDIA CUDA, Platform Version = OpenCL 1.0 CUDA 3.2.1, SDK Revision = 7027912, NumDevs = 1, Device = GeForce GTX 465

System Info:

 Local Time/Date = 18:18:22, 11/17/2010
 CPU Arch: 0
 CPU Level: 6
 # of CPU processors: 4
 Windows Build: 6002
 Windows Ver: 6.0 (Windows Vista / Windows 7)


PASSED


Press <Enter> to Quit...
-----------------------------------------------------------

2083
3D-Tech News Around The Web / PC Wizard 2010 v1.96
« on: November 17, 2010, 05:43:06 PM »
Download here until website is updated:
ftp://ftp.cpuid.com/pc-wizard/pc-wizard_2010.1.96-setup.exe (64 & 32 bit)
ftp://ftp.cpuid.com/pc-wizard/pc-wizard_2010.1.96.zip (32 bit)

Quote
PC Wizard 2010 Release Notes
Copyright © 1996-2010 Laurent KUTIL & Franck DELATTRE
 
2010/08/24
- Intel Atom N455, N475 processors support
- Intel Atom D425, D525 processors support
- Intel Pentium E6700, E5700 processors support
- Intel Core i3 330E, Core i7 660UE processors support
- Intel Celeron U3400, U3405 processors support

2010/08/26
- Sony ACPI Thermal Zones support
- nVidia SLI Ready Motherboard detection support

2010/08/30
- ATI HD6xxx Cayman, Antilles, BlackComb, Barts, Whistler, Onega, Turks, Seymour, Caicos video cards preliminary support
- Intel SandyBridge improved support
- Intel Core i7 2600K, 2600, 2600S, 2920XM, 2820QM, 2720QM, 2620M processors support
- Intel Core i5 2500K, 2500, 2500S, 2500T, 2400, 2400S, 2390T, 2540M, 2520M processors support
- Intel Core i3 2120, 2100T processors support

2010/09/04
- Nuvoton NCT6776 hardware sensor support
- AMD Lightwieght Profiling processor support
- AMD XOP, FMA4, TBM, F16C, BMI features processor support
- nVIDIA GTS450, GTS455 video card support
- Microsoft Internet Explorer 9 Beta support

2010/10/03
- Intel Core i7 680UM, 660LM, 640M processors support
- Intel Core i5 580M, 560UM, 560M, 470UM, 460M processors support
- Intel Core i3 380M, 380UM processor support
- Intel Pentium P6100, P6200 processors support
- Intel Celeron T3500, P4600, P4500 processors support
- Intel Xeon X5690 processor support

2010/10/30
- nVidia GTX580 video card prelmiminary support
- HP Hardware Sensor CMI support
- Intel Core i7 995/995X processor support
- Intel Core i3 560 processor support

2010/11/09
- nVidia Video Cards external connectors type detection support
- nVidia Video Cards Activity Load support
- ATI Eyefinity information support

2010/11/16
- Devices plugged or removed auto-detection support

Multiple OpenCL vendors are recognised correctly.


2084
Intel OpenCL SDK tested on desktop with NVIDIA GPU and Core2Quad 9450



NVIDIA's OpenCL Device Query fails to recognise Intel platform.



GPUCapsviewer recognises NVIDIA and Intel platform, but is confused and continues using NVIDIA platform, albeit Intel is selected.





AMD's Stream 2.2 CLINFO recognises NVIDIA and Intel platform, but prints some errors:

Code: [Select]
Number of platforms: 2
  Platform Profile: FULL_PROFILE
  Platform Version: OpenCL 1.0 CUDA 3.2.1
  Platform Name: NVIDIA CUDA
  Platform Vendor: NVIDIA Corporation
  Platform Extensions: cl_khr_byte_addressable_store cl_khr_icd cl_khr_gl_sharing cl_nv_d3d9_sharing cl_nv_d3d10_sharing cl_khr_d3d10_sharing cl_nv_d3d11_sharing cl_nv_compiler_options cl_nv_device_attribute_query cl_nv_pragma_unroll
  Platform Profile: FULL_PROFILE
  Platform Version: OpenCL 1.1 WINDOWS
  Platform Name: Intel OpenCL
  Platform Vendor: Intel Corporation
  Platform Extensions: cl_khr_fp64 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_gl_sharing cl_khr_byte_addressable_store cl_khr_icd


  Platform Name: NVIDIA CUDA
Number of devices: 1
  Device Type: CL_DEVICE_TYPE_GPU
  Device ID: 4318
  Max compute units: 11
  Max work items dimensions: 3
    Max work items[0]: 1024
    Max work items[1]: 1024
    Max work items[2]: 64
  Max work group size: 1024
  Preferred vector width char: 1
  Preferred vector width short: 1
  Preferred vector width int: 1
  Preferred vector width long: 1
  Preferred vector width float: 1
  Preferred vector width double: 1
  Max clock frequency: 810Mhz
  Address bits: 17240136165097504
  Max memory allocation: 260423680
  Image support: Yes
  Max number of images read arguments: 128
  Max number of images write arguments: 8
  Max image 2D width: 4096
  Max image 2D height: 32768
  Max image 3D width: 2048
  Max image 3D height: 2048
  Max image 3D depth: 2048
  Max samplers within kernel: 16
  Max size of kernel argument: 4352
  Alignment (bits) of base address: 4096
  Minimum alignment (bytes) for any datatype: 128
  Single precision floating point capability
    Denorms: Yes
    Quiet NaNs: Yes
    Round to nearest even: Yes
    Round to zero: Yes
    Round to +ve and infinity: Yes
    IEEE754-2008 fused multiply-add: Yes
  Cache type: Read/Write
  Cache line size: 128
  Cache size: 180224
  Global memory size: 1041694720
  Constant buffer size: 65536
  Max number of constant args: 9
  Local memory type: Scratchpad
  Local memory size: 49152
  Profiling timer resolution: 1000
  Device endianess: Little
  Available: Yes
  Compiler available: Yes
  Execution capabilities:
    Execute OpenCL kernels: Yes
    Execute native function: No
  Queue properties:
    Out-of-Order: Yes
    Profiling : Yes
  Platform ID: 02551550
  Name: GeForce GTX 465
  Vendor: NVIDIA Corporation
  Driver version: 261.00
  Profile: FULL_PROFILE
  Version: OpenCL 1.0 CUDA
  Extensions: cl_khr_byte_addressable_store cl_khr_icd cl_khr_gl_sharing cl_nv_d3d9_sharing cl_nv_d3d10_sharing cl_khr_d3d10_sharing cl_nv_d3d11_sharing cl_nv_compiler_options cl_nv_device_attribute_query cl_nv_pragma_unroll  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_fp64


Error : atomics mismatch!
Error : Bytes mismatch!
Error : d3d10Sharing mismatch!
Error : glSharing mismatch!
Error : images mismatch!
Error : printf mismatch!
Error : deviceAttributeQuery mismatch!
Failed!
  Platform Name: Intel OpenCL
Number of devices: 1
  Device Type: CL_DEVICE_TYPE_CPU
  Device ID: 32902
  Max compute units: 4
  Max work items dimensions: 3
    Max work items[0]: 1024
    Max work items[1]: 1024
    Max work items[2]: 1024
  Max work group size: 1024
  Preferred vector width char: 16
  Preferred vector width short: 8
  Preferred vector width int: 4
  Preferred vector width long: 2
  Preferred vector width float: 4
  Preferred vector width double: 2
  Max clock frequency: 3200Mhz
  Address bits: 17240136165097504
  Max memory allocation: 536838144
  Image support: Yes
  Max number of images read arguments: 128
  Max number of images write arguments: 128
  Max image 2D width: 8192
  Max image 2D height: 8192
  Max image 3D width: 2048
  Max image 3D height: 2048
  Max image 3D depth: 2048
  Max samplers within kernel: 128
  Max size of kernel argument: 1024
  Alignment (bits) of base address: 1024
  Minimum alignment (bytes) for any datatype: 128
  Single precision floating point capability
    Denorms: Yes
    Quiet NaNs: Yes
    Round to nearest even: Yes
    Round to zero: No
    Round to +ve and infinity: No
    IEEE754-2008 fused multiply-add: No
  Cache type: Read/Write
  Cache line size: 64
  Cache size: 6291456
  Global memory size: 2147352576
  Constant buffer size: 131072
  Max number of constant args: 128
  Local memory type: Global
  Local memory size: 32768
  Profiling timer resolution: 279
  Device endianess: Little
  Available: Yes
  Compiler available: Yes
  Execution capabilities:
    Execute OpenCL kernels: Yes
    Execute native function: Yes
  Queue properties:
    Out-of-Order: Yes
    Profiling : Yes
  Platform ID: 02E11220
  Name: GenuineIntel
  Vendor: Intel Corporation
  Driver version: 1.1
  Profile: FULL_PROFILE
  Version: OpenCL 1.1
  Extensions: cl_khr_fp64 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_gl_sharing cl_khr_byte_addressable_store


Error : atomics mismatch!
Error : Bytes mismatch!
Error : d3d10Sharing mismatch!
Error : glSharing mismatch!
Error : images mismatch!
Error : printf mismatch!
Error : deviceAttributeQuery mismatch!
Failed!

2085
3D-Tech News Around The Web / Intel releases OpenCL SDK
« on: November 16, 2010, 06:37:51 PM »
As i predicted earlier, Intel released their own OpenCL SDK to be demonstrated at SC10.

I will do some tests asap...


2086
Quote
For professional users operating on Mac OS X Snow Leopard, this means the wait is over. The NVIDIA Quadro 4000 graphics processing unit (GPU) for Mac is optimized to accelerate workflows and drive a range of top professional applications.

Full story @ TPU

Download corresponding Quadro Mac OS X Driver Release 256.01.00f03

2087
3D-Tech News Around The Web / AMD lists rebranded HD6000 GPUS
« on: November 15, 2010, 06:51:55 PM »
Rebranded GPUs have the codename "Evergreen", really new GPUs have the codename "NI" (Northern Islands)

Full list here: ATI Catalyst™ PC VENDOR ID (1002) LIST

Quote
{ “ATI Radeon HD 6230   , Evergreen,   68F9”}
{ “ATI Radeon HD 6250   , Evergreen,   68F9”}
{ “ATI Radeon HD 6290   , Evergreen   ,68F9”}
{ “ATI Radeon HD 6390   , Evergreen,   68DA”}
{ “ATI Radeon HD 6510   , Evergreen,   68D9”}
{ “ATI Radeon HD 6750   , Evergreen   ,68BE”}
{ “ATI Radeon HD 6230     , Evergreen   ,68F9”}
{ “ATI Radeon HD 6250     , Evergreen   ,68F9”}
{ “ATI Radeon HD 6290     , Evergreen,   68F9”}
{ “ATI Radeon HD 6390     , Evergreen   ,68DA”}
{ “ATI Radeon HD 6510     , Evergreen   ,68D9”}
{ “ATI Radeon HD 6750     , Evergreen,   68BE”}

[via]

2088
3D-Tech News Around The Web / Alenka - SQL engine for CUDA
« on: November 15, 2010, 06:14:08 PM »
Quote
Alenka is a high level, high performance SQL-like language for data processing on CUDA hardware. All SQL operations like joins, groupings and sorts are implemented in a highly parallel fashion. Alenka uses regular files as sources of data. Read data are stored internally as columns, all operations are vector operations and thus are highly scalable on NVIDIA GPUs.

To use Alenka you need a GPU that supports CUDA 1.3 and higher (cards of models GTX 200 or GTX 400).

2089
3D-Tech News Around The Web / Notepad++ 5.8.4 released
« on: November 15, 2010, 05:18:00 PM »
Quote
Notepad++ v5.8.4 new features and fixed bugs (from v5.8.3):

   1. Fix memory leak problem while switching tab.
   2. Fix User Defined Language dialog docking problem under Windows 7.
   3. Fix backwards search with Asian codepage problem.
   4. Add a new capacity in context menu: the menu item and folder item can be renamed (and in whichever language).
   5. All the supported encoding charsets can be set as default in "New Document Settings".
   6. Remove Calltip restriction from plugins side.
   7. Add "-alwaysOnTop" command line argument.
   8. Fix icon display glitch in shell extension context menu.

2090
3D-Tech News Around The Web / VLC media player 1.1.5 final
« on: November 14, 2010, 10:57:02 AM »
Quote
What's new in 1.1.5

Two and a half months after VLC 1.1.4, and after almost 50 million downloads of VLC 1.1.4, here is a minor release of VLC 1.1.5.

Introducing small features and fixing important bug and a security issue, here is VLC 1.1.5.

    * 1000 Web-shows listing integrated inside VLC's playlist, provided by Channels.com
    * New Game Music Emu (GME) support
    * Windows SMB security issue - VideoLAN-SA-1006
    * Major updates in translations, and new translations in Asturian, Armenian and Modern Greek
    * Mac/Power-PC port fixed in 1.1.4.1
    * live .webm streams support
    * GPU HD decoding using Intel IGP on Windows, using DxVA2
    * Miscellaneous fixes on all Interfaces, Demuxers and Decoders modules
    * Codecs updates

The chipmunk shows you how to enable GPU acceleration  ;D


2091
Quote
NVIDIA shook the high-end PC hardware industry earlier this month with the surprise launch of its GeForce GTX 580 graphics card, which extended the lead for single-GPU performance NVIDIA has been holding. It also managed to come up with some great performance per Watt improvements over the previous generation. The reference design board, however, made use of a clock speed throttling logic which reduced clock speeds when an extremely demanding 3D application such as Furmark or OCCT is run. While this is a novel way to protect components saving consumers from potentially permanent damage to the hardware, it does come as a gripe to expert users, enthusiasts and overclockers, who know what they're doing.

GPU-Z developer and our boss W1zzard has devised a way to make disabling this protection accessible to everyone (who knows what he's dealing with), and came up with a nifty new feature for GPU-Z, our popular GPU diagnostics and monitoring utility, that can disable the speed throttling mechanism. It is a new command-line argument for GPU-Z, that's "/GTX580OCP". Start the GPU-Z executable (within Windows, using Command Prompt or shortcut), using that argument, and it will disable the clock speed throttling mechanism. For example, "X:gpuz.exe /GTX580OCP" It will stay disabled for the remainder of the session, you can close GPU-Z. It will be enabled again on the next boot.



As an obligatory caution, be sure you know what you're doing. TechPowerUp is not responsible for any damage caused to your hardware by disabling that mechanism. Running the graphics card outside of its power specifications may result in damage to the card or motherboard. We have a test build of GPU-Z (which otherwise carries the same-exact feature-set of GPU-Z 0.4.8). We also ran a power consumption test on our GeForce GTX 580 card demonstrating how disabling that logic affects power consumption.

DOWNLOAD: TechPowerUp GPU-Z GTX 580 OCP Test Build

P.S.
this build is newer than the builds in the previous post today

2092
Quote
Have you wondered how DX11 tessellation help a game look better? Check out this video to see a DX11 Tessellation On/Off comparison featuring Tom Clancy's H.A.W.X. 2 on an NVIDIA GeForce graphics card. You'll notice the incredibly detailed terrain and environments when tessellation is turned on.


2093
3D-Tech News Around The Web / ATI Catalyst 8.791 @ MS Update
« on: November 13, 2010, 05:03:43 PM »
Attention: this driver "1011041549-8.791-101026a-107889C-ATI" does not expose OpenGL 4.1 and the profiles in UMD are older than in "Hotfix E 8.782.1"
Don't get fooled by version numbers!

Direct downloads:
Vista/7 64
Vista/7 32
XP 32
XP 64



2094
Tune into our webinars to listen to AMD experts discuss and answer questions about data parallel computing on GPUs leveraging the OpenCL™ architecture.

Download slides:
# Introduction to Parallel and Heterogeneous Computing
# Introduction to OpenCL
# GPU Architecture Overview
# OpenCL Programming in Detail

2095
Fix for BIOS reading on GTX 580 (11.11.2010)

Support for "GeForce GT220 with GT215 GPU" (13.11.2010) - i assume it also contains the fix from the first link

EDIT:
A yet newer build can be found here

2096
3D-Tech News Around The Web / OpenGL Extensions Viewer 3.34 available
« on: November 13, 2010, 03:56:03 PM »
You can download the latest version of OpenGL Extensions Viewer here.
No changelog atm

The bug in 3.33 has been fixed, now .NET crashes rendering test in windowed mode (protected memory)





2097
3D-Tech News Around The Web / Unity3D version 3.1
« on: November 13, 2010, 06:44:53 AM »
Download Unity3D (worked only with IE for me)

Quote
Additional Improvements & Fixes

As usual, we added a couple of improvements and fixed some things...
New Features:

    * Managed .NET DLLs can now be placed in the project folder and can contain script code, including MonoBehaviours, EditorWindows and ScriptableObjects. This allows you to move any code into a DLL, making code sharing between projects easier, and making it easier for middleware developers to create libraries without sharing the source code. This was introduced in Unity 3.0 but was not mentioned in the release notes.
    * Scripting: Added GL.InvalidateState() to flush the internal renderstate cache in Unity. This is mostly useful when writing native code plugins that access the 3D device.
    * Audio: Added AudioSettings.outputSampleRate. Returns the mixer's output rate; use this to calculate the precise hertz range returned from GetSpectrumData().

Fixes:

    * Editor: Fixed out of memory errors when editing very large terrains due to the Undo system.
    * Editor: Fixed "too many open files" error when reimporting a large project with many shaders on Mac OS X.
    * Editor: Some textures would not say "Texture not yet compressed" when importing with the "Compress Textures" preference turned off.
    * Editor: Fixed a bug where upgrading a Unity 2.x project with normal maps would leave some normal maps not marked as Normalmap type properly.
    * Terrain Engine: Unity 2.x Soft Vegetation tree shaders had lighting upside down :)
    * Shaders: fixed Surface Shader compilation errors with large custom output structures.
    * Shaders: wrong syntax in UnityCG.glslinc file (for GLSL shaders).
    * Graphics: fixed Projector crash in some circumstances.
    * Graphics: fixed tangent vectors not bound correctly with GLSL shaders on some GPUs.
    * Graphics: fixed dynamic batching corrupting vertex colors on Direct3D.
    * Graphics: fixed GL.TRIANGLES rendering with large triangle counts on Direct3D.
    * Graphics: fixed some hiccups when changing non-uniform scale of meshes.
    * Graphics: Fixed dynamic batching index overflow.
    * Audio: GetOutputData/GetSpectrumData API changed so it accepts an pre-allocated array instead of allocating on every call. Old API is deprecated and marked obsolete.

Unity iOS Fixes:

    * Fixed render texture support on iPad with OS 3.2.
    * Fixed video autorotation. Pinch zoom gesture now disabled during video playback.
    * Fixed stripping of GUI scrollable area.
    * Fixed OpenGL ES 1.1 cache invalidation, which was sometimes causing visual artifacts.
    * Fixed render texture memory leak.

Unity Android Improvements & Fixes:

    * Plugins folder is moved; it now uses Assets/Plugins/Android to scan for plugins.
    * Plugins now support standard Android project layout; /assets, /bin, /libs and /res will be merged with the final package.
    * Added 'update necessary' notifcation dialog for Samsung devices running pre-2.2 OS firmware.
    * License Verification Library (LVL) no longer causes a crash.
    * Added iPhoneUtils.isApplicationGenuineAvailable() to be able to determine if application integrity can be confirmed or not.
    * Ignore .meta files (with external version control) when packaging the .apk.
    * Assign DefaultImporter to platform specific plugin assets.
    * Custom manifests are now merged with the properties from the editor (like Bundle Identifier, Version and permission flags).
    * Ship UnityPlayerActivity as source code template for writing plugins with custom activity classes.
    * Added support for translucent (RGBA 8888) rendering surface.
    * com/unity3d/player/UnityPlayerActivity.currentActivity field is now found at com/unity3d/player/UnityPlayer.currentActivity.
    * iPhoneKeyboard is now displayed on top of the application; it supports the basic soft keyboard layouts (URL, Email, Phone, etc).
    * PlayMovie is now displayed on top of the application (instead of in a separate activity); fixes the screenCanDarken issue while playing movies.
    * The editor now checks for device specifications before trying to deploy in Build&Run.
    * The editor will try to locate the JDK based on information stored in the registry on Windows.
    * Fixed C# assemblies being loaded from the wrong thread; was causing crashes if external classes were loaded late at runtime.
    * Fixed render textures on OpenGL ES 2.0.

2098
AMD messed up their download sites again. If the direct downloads: Hotfix 10.10E and CAP2 fail, visit following topics at Rage3D:

AMD Hotfix Catalyst 10.10e With MLAA For Radeon HD 5000 Series Now Available
Rage3D Exclusive - New AMD Catalyst Application Profile 10.10 #2!

2099
Quote
This CUDA experiment maps a FULL-HD (1920x1080 @ 30 frames per second, MPEG2 compression) video source into 3D space. Each frame is processed in real-time on the GPU using CUDA. Each pixel in a frame (2.073.600 pixels per frame) is scaled by its luminance value and given the original color. The camera flight is realized with a 3D space navigator in real-time. This application is written in C# using DirectX 11, CUDA.NET and DirectShow.NET libraries. Benchmarks: GPU load is about 85% (GTX 260), GPU memory controller load 25%, CPU (i7-920) is at 20%.

For more information about this experiment visit:
http://www.visualcompute.com/
http://www.noumentalia.de/

2100
Developers may download it here

Quote
Release Notes - NVIDIA PhysX SDK 2.8.4
November 12th 2010
What's New In NVIDIA PhysX 2.8.4
General

    * Discontinued the Training Programs.
    * Added source code of NxTetra (tet-maker) utility to source distribution.
    * Removed spin waits from sample code.
    * Added API to permit the user to specify the order in which compartments are simulated.
    * Added compression limits to cloth.
    * Cloth simulation no longer performs prediction for kinematic rigid bodies for improved interaction behavior.
    * New 'driverless' PhysXLoader for PC CPU distribution.
      In 2.8.4, application developers must ship PhysXCore.dll, PhysXCooking.dll, the cudarXX_XX_X.dll and physxdevice.dll with the application 'locally', in the directory where the .exe is located:
          o The application requests PhysXCore or PhysXCooking (v 2.8.4) from the PhysXLoader.
          o PhysXLoader searches for another DLL called 'PhysXUpdateLoader'.
          o If PhysXUpdateLoader is not found, PhysXLoader will load the local PhysXCore or PhysXCooking.
          o If PhysXUpdateLoader is found, it looks for an updated replacement for the PhysXCore or PhysXCooking dlls.
          o If PhysXUpdateLoader cannot find the specified replacement DLL, PhysXLoader will load the local PhysXCore or PhysXCooking dlls.
          o If PhysXUpdateLoader can find the replacement DLLs, these will be loaded in place of the local PhysCore or PhysXCooking dlls.
    * The net result is that the developer has more control over the game installation process, doesn't have to worry about shipping a large System Software with the game, doesn't have to worry that the player will break his System Software somehow, etc.
    * Better rotation matrix input validity checking.
    * Made Desc::isValid() more verbose.
    * CUDA errors are now reported to the debug stream.
    * Added extended scene statistics for GPU memory usage.
    * Lowered the default GPU memory heap size to 32 MB from 128 MB. You may use NxPhysicsSDKDesc::gpuHeapSize to change how much GPU memory is allocated for physics.
    * Disabled GPU acceleration by default. Clear NX_SDF_NO_HARDWARE to enable it.
    * Corrected inertia and volume computation for capsule. For the same capsule dimension and density, the mass and inertia is slightly different compared to the previous release.

Supported Devices

    * The supported devices are the same as for PhysX 2.8.1 (see below), except that the AGEIA PhysX Processor (PPU) device support was removed.

Performance

    * Enabled /arch:SSE2 compiler switch for all optimized PC builds.
    * Optimized PS3 SPU Memory Manager
    * Optimized AgPerfmon AgPerfUtils wrapper
    * Optimized cloth simulation on PS3, XBOX 360, PC CPU

Fixed Bugs

    * Debugged PS3 SPU Memory Manager
    * Fluids now collide properly when static shapes are removed or added.
    * Fixed crash bug in character controller sample.
    * Fixed a number of bugs in the HSM.
    * In the event of a CUDA error (typically a failed launch or an inadequately sized CUDA memory heap), the NxFluid will not allow the addition of any more particles.

Known Issues and Limitations

    * Please also see the previous lists from 2.8.3 and earlier.

API changes

    * Cloth
          o NxCloth::getShapePointers() no longer returns shape flags.
          o Added methods to NxCloth and members to NxClothDesc to set compression parameters.
          o NxCloth::setFlag() can no longer be used to change NX_CLF_BENDING_ORTHO, use flag in NxClothDesc instead.
    * Fluids
          o Removed NxFluidFlag::NX_FF_ENABLE_STATIC_FRICTION. Static friction is enabled by default now.
    * Removed NX_SDKF_EXTENDED_DESCRIPTOR.
    * Added NxPhysicsSDK::resizeGpuHeap() to allow changing the GPU heap size after SDK creation. See the GPU Memory section of the User's Guide for details.
    * NxPhysicsSDKDesc::flags has NX_SDKF_NO_HARDWARE set by default.
    * Added checkValid() method to descriptors that return an error code instead of the boolean of isValid().
    * The experimental NxScene::simulateCompartments() method has been added. It gives more control over the order in which compartments get simulated.

Pages: 1 ... 103 104 [105] 106 107 ... 162