Posts by macintel

1) Message boards : GPUs : OS X 10.9 Mavericks and Nvidia GPUs (Message 51057)
Posted 28 Oct 2013 by macintel
Post:
OS X 10.9 Mavericks

Hello, i´ve got GPU pstate problems with OS X 10.9, Nvidia GTS650 and Boinc 7.2.23.

if i start a GPU task my GPU works with highest pstate as it should but
behind i stopped the task the pstate won´t throotle down and stood still there with the
highest pstate. this won´t appear in OS X 10.8.5
2) Message boards : Questions and problems : Mac OS X 10.7.3 OpenCL (Message 42573)
Posted 15 Feb 2012 by macintel
Post:
hello, i used the final combo update 10.7.3 (11D50) and tried (11D50b) too.
behind used the latestest cudadrivers_4.1.28_macos (and 4.1.29), cudatoolkit_4.1.28_macos and sdk.

but Boinc 7.0.15 (and before) won´t find OpenCL with 10.7.3 GeForceGLDriver.bundle 7.18.11

but with GeForceGLDriver.bundle 7.12.9 from 10.7.2:
NVIDIA GPU 0: GeForce GTS 450 (driver version 4.1.29, CUDA version 4.10, compute capability 2.1, 1024MB, 889MB available, 653 GFLOPS peak)
OpenCL: NVIDIA GPU 0: GeForce GTS 450 (driver version CLH 1.0, device version OpenCL 1.1, 1024MB, 889MB available)

The GTS450 shows with Collatz3.06 openCL slot 0 and with BRBCuda32OSX slot 1 is this right ?

could it be that 10.7.3 has a different driver as version CLH 1.0 and won´t be recognized ?

ps: luxmark opencl benchmark find my gts450 with the 10.7.3 driverbundle
3) Message boards : Questions and problems : Mac OS X 10.7.3 OpenCL (Message 42545)
Posted 12 Feb 2012 by macintel
Post:
Hello,
behind the 10.7.3 update the Boinc Client V.7.0.15 won´t reconice OpenCL of my NVIDIA Gts450.
I have to rollback the GeForceGLDriver.bundle to 10.7.2
NVIDIA GPU 0: GeForce GTS 450 (driver version 4.1.28, CUDA version 4.10, compute capability 2.1, 1024MB, 718MB available, 653 GFLOPS peak)
OpenCL: NVIDIA GPU 0: GeForce GTS 450 (driver version CLH 1.0, device version OpenCL 1.1, 1024MB, 718MB available)

The Install Pkg. of V. 7 won´t work in 10.7.3 too
4) Message boards : Questions and problems : Mac user GPU (Message 37474)
Posted 13 Apr 2011 by macintel
Post:
Hello, iám brand new and just installed the latest Boinc Client on OS X 10.6.7

got latest Cuda driver, toolkit and tools 4.0 RC2 installed.

bash-3.2# cd /Developer/GPU\ Computing/C/bin/darwin/release 
bash-3.2# ./devicequery
[./devicequery] starting...
./devicequery Starting...

 CUDA Device Query (Runtime API) version (CUDART static linking)

There is 1 device supporting CUDA

Device 0: "GeForce GTS 450"
  CUDA Driver Version / Runtime Version          4.0 / 4.0
  CUDA Capability Major/Minor version number:    2.1
  Total amount of global memory:                 1024 MBytes (1073283072 bytes)
  ( 4) Multiprocessors x (48) CUDA Cores/MP:     192 CUDA Cores
  GPU Clock Speed:                               1.57 GHz
  Memory Clock rate:                             1804.00 Mhz
  Memory Bus Width:                              128-bit
  L2 Cache Size:                                 262144 bytes
  Max Texture Dimension Size (x,y,z)             1D=(65536), 2D=(65536,65535), 3D=(2048,2048,2048)
  Max Layered Texture Size (dim) x layers        1D=(16384) x 2048, 2D=(16384,16384) x 2048
  Total amount of constant memory:               65536 bytes
  Total amount of shared memory per block:       49152 bytes
  Total number of registers available per block: 32768
  Warp size:                                     32
  Maximum number of threads per block:           1024
  Maximum sizes of each dimension of a block:    1024 x 1024 x 64
  Maximum sizes of each dimension of a grid:     65535 x 65535 x 65535
  Maximum memory pitch:                          2147483647 bytes
  Texture alignment:                             512 bytes
  Concurrent copy and execution:                 Yes with 2 copy engine(s)
  Run time limit on kernels:                     Yes
  Integrated GPU sharing Host Memory:            No
  Support host page-locked memory mapping:       Yes
  Concurrent kernel execution:                   Yes
  Alignment requirement for Surfaces:            Yes
  Device has ECC support enabled:                No
  Device is using TCC driver mode:               No
  Device supports Unified Addressing (UVA):      No
  Device PCI Bus ID / PCI location ID:           1 / 0
  Compute Mode:
     < Default (multiple host threads can use ::cudaSetDevice() with device simultaneously) >

deviceQuery, CUDA Driver = CUDART, CUDA Driver Version = 4.0, CUDA Runtime Version = 4.0, NumDevs = 1, Device = GeForce GTS 450
[./devicequery] test results...
PASSED

Press ENTER to exit...


Collatz Conjecture | Requesting new tasks for NVIDIA GPU

but mini_collatz_2.02_x86_64-apple-darwin__cuda won´t work for me.

got the same error with Cuda 3.2 before too

is there any Cuda app working in 64 bit?

thx in advance




Copyright © 2024 University of California.
Permission is granted to copy, distribute and/or modify this document under the terms of the GNU Free Documentation License, Version 1.2 or any later version published by the Free Software Foundation.