cs344 »

CS344/devicequery


The following is the Device Query information for the Amazon EC2 GPUs that Udacity uses as the class backend

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

Detected 2 CUDA Capable device(s)

Device 0: "Tesla M2050"
   CUDA Driver Version / Runtime Version 5.0 / 5.0
   CUDA Capability Major/Minor version number: 2.0
   Total amount of global memory: 2687 MBytes (2817982464 bytes)
   (14) Multiprocessors x ( 32) CUDA Cores/MP: 448 CUDA Cores
   GPU Clock rate: 1147 MHz (1.15 GHz)
   Memory Clock rate: 1546 Mhz
   Memory Bus Width: 384-bit
   L2 Cache Size: 786432 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 multiprocessor: 1536
   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 kernel execution: Yes with 2 copy engine(s)
   Run time limit on kernels: No
   Integrated GPU sharing Host Memory: No
   Support host page-locked memory mapping: Yes
   Alignment requirement for Surfaces: Yes
   Device has ECC support: Enabled
   Device supports Unified Addressing (UVA): Yes
   Device PCI Bus ID / PCI location ID: 0 / 3
   Compute Mode: < Exclusive Process (many threads in one process is able to use ::cudaSetDevice() with this device) >


Device 1: "Tesla M2050"    CUDA Driver Version / Runtime Version 5.0 / 5.0
   CUDA Capability Major/Minor version number: 2.0
   Total amount of global memory: 2687 MBytes (2817982464 bytes)
   (14) Multiprocessors x ( 32) CUDA Cores/MP: 448 CUDA Cores
   GPU Clock rate: 1147 MHz (1.15 GHz)
   Memory Clock rate: 1546 Mhz
   Memory Bus Width: 384-bit
   L2 Cache Size: 786432 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 multiprocessor: 1536
   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 kernel execution: Yes with 2 copy engine(s)
   Run time limit on kernels: No
   Integrated GPU sharing Host Memory: No
   Support host page-locked memory mapping: Yes
   Alignment requirement for Surfaces: Yes
   Device has ECC support: Enabled
   Device supports Unified Addressing (UVA): Yes
   Device PCI Bus ID / PCI location ID: 0 / 4
   Compute Mode: < Exclusive Process (many threads in one process is able to use ::cudaSetDevice() with this device) >

deviceQuery, CUDA Driver = CUDART, CUDA Driver Version = 5.0, CUDA Runtime Version = 5.0, NumDevs = 2, Device0 = Tesla M2050, Device1 = Tesla M2050