NVIDIA TITAN X a szerverekben, azaz jonnek a deep learning platformok

a laborban tobben foglalkoznak machine learning/neuralis halozatokkal, igy szukseges volt beszereznunk par gepet GPU-kkal. az amerikai testverlaborunkban van egy eleg combos cluster (sok szaz gep, gepenkent 4 GPU, infiniband halozat, XIV storage alatta), de gondoltuk jo lenne valami kis helyi is...

kepeim nincsenek, mivel mostanaban fizikailag nem nagyon vagyok a laborban (minden heten ugyfelnel vagyok), de a kollegammal beszereltettem a gepeket (2x8 mag, 128GB RAM), MaaS-sal felhuztam pikk-pakk, es mar lehetett is hasznalni.

az NVIDIA-nak van a CUDA-bol repoja is, ugyhogy a repo behuzasa utan apt-get update, apt-get install cuda siman felrak mindent, DKMS-sel. 


oot@gpu3:~/cuda/NVIDIA_CUDA-7.5_Samples# bin/x86_64/linux/release/deviceQuery
bin/x86_64/linux/release/deviceQuery Starting...

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

Detected 4 CUDA Capable device(s)

Device 0: "GeForce GTX TITAN X"
  CUDA Driver Version / Runtime Version          7.5 / 7.5
  CUDA Capability Major/Minor version number:    5.2
  Total amount of global memory:                 12288 MBytes (12884705280 bytes)
  (24) Multiprocessors, (128) CUDA Cores/MP:     3072 CUDA Cores
  GPU Max Clock rate:                            1076 MHz (1.08 GHz)
  Memory Clock rate:                             3505 Mhz
  Memory Bus Width:                              384-bit
  L2 Cache Size:                                 3145728 bytes
  Maximum Texture Dimension Size (x,y,z)         1D=(65536), 2D=(65536, 65536), 3D=(4096, 4096, 4096)
  Maximum Layered 1D Texture Size, (num) layers  1D=(16384), 2048 layers
  Maximum Layered 2D Texture Size, (num) layers  2D=(16384, 16384), 2048 layers
  Total amount of constant memory:               65536 bytes
  Total amount of shared memory per block:       49152 bytes
  Total number of registers available per block: 65536
  Warp size:                                     32
  Maximum number of threads per multiprocessor:  2048
  Maximum number of threads per block:           1024
  Max dimension size of a thread block (x,y,z): (1024, 1024, 64)
  Max dimension size of a grid size    (x,y,z): (2147483647, 65535, 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:                        Disabled
  Device supports Unified Addressing (UVA):      Yes
  Device PCI Domain ID / Bus ID / location ID:   0 / 2 / 0
  Compute Mode:
     < Default (multiple host threads can use ::cudaSetDevice() with device simultaneously) >

Device 1: "GeForce GTX TITAN X"
  CUDA Driver Version / Runtime Version          7.5 / 7.5
  CUDA Capability Major/Minor version number:    5.2
  Total amount of global memory:                 12288 MBytes (12884705280 bytes)
  (24) Multiprocessors, (128) CUDA Cores/MP:     3072 CUDA Cores
  GPU Max Clock rate:                            1076 MHz (1.08 GHz)
  Memory Clock rate:                             3505 Mhz
  Memory Bus Width:                              384-bit
  L2 Cache Size:                                 3145728 bytes
  Maximum Texture Dimension Size (x,y,z)         1D=(65536), 2D=(65536, 65536), 3D=(4096, 4096, 4096)
  Maximum Layered 1D Texture Size, (num) layers  1D=(16384), 2048 layers
  Maximum Layered 2D Texture Size, (num) layers  2D=(16384, 16384), 2048 layers
  Total amount of constant memory:               65536 bytes
  Total amount of shared memory per block:       49152 bytes
  Total number of registers available per block: 65536
  Warp size:                                     32
  Maximum number of threads per multiprocessor:  2048
  Maximum number of threads per block:           1024
  Max dimension size of a thread block (x,y,z): (1024, 1024, 64)
  Max dimension size of a grid size    (x,y,z): (2147483647, 65535, 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:                        Disabled
  Device supports Unified Addressing (UVA):      Yes
  Device PCI Domain ID / Bus ID / location ID:   0 / 3 / 0
  Compute Mode:
     < Default (multiple host threads can use ::cudaSetDevice() with device simultaneously) >

Device 2: "GeForce GTX TITAN X"
  CUDA Driver Version / Runtime Version          7.5 / 7.5
  CUDA Capability Major/Minor version number:    5.2
  Total amount of global memory:                 12288 MBytes (12884705280 bytes)
  (24) Multiprocessors, (128) CUDA Cores/MP:     3072 CUDA Cores
  GPU Max Clock rate:                            1076 MHz (1.08 GHz)
  Memory Clock rate:                             3505 Mhz
  Memory Bus Width:                              384-bit
  L2 Cache Size:                                 3145728 bytes
  Maximum Texture Dimension Size (x,y,z)         1D=(65536), 2D=(65536, 65536), 3D=(4096, 4096, 4096)
  Maximum Layered 1D Texture Size, (num) layers  1D=(16384), 2048 layers
  Maximum Layered 2D Texture Size, (num) layers  2D=(16384, 16384), 2048 layers
  Total amount of constant memory:               65536 bytes
  Total amount of shared memory per block:       49152 bytes
  Total number of registers available per block: 65536
  Warp size:                                     32
  Maximum number of threads per multiprocessor:  2048
  Maximum number of threads per block:           1024
  Max dimension size of a thread block (x,y,z): (1024, 1024, 64)
  Max dimension size of a grid size    (x,y,z): (2147483647, 65535, 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:                        Disabled
  Device supports Unified Addressing (UVA):      Yes
  Device PCI Domain ID / Bus ID / location ID:   0 / 129 / 0
  Compute Mode:
     < Default (multiple host threads can use ::cudaSetDevice() with device simultaneously) >

Device 3: "GeForce GTX TITAN X"
  CUDA Driver Version / Runtime Version          7.5 / 7.5
  CUDA Capability Major/Minor version number:    5.2
  Total amount of global memory:                 12288 MBytes (12884705280 bytes)
  (24) Multiprocessors, (128) CUDA Cores/MP:     3072 CUDA Cores
  GPU Max Clock rate:                            1076 MHz (1.08 GHz)
  Memory Clock rate:                             3505 Mhz
  Memory Bus Width:                              384-bit
  L2 Cache Size:                                 3145728 bytes
  Maximum Texture Dimension Size (x,y,z)         1D=(65536), 2D=(65536, 65536), 3D=(4096, 4096, 4096)
  Maximum Layered 1D Texture Size, (num) layers  1D=(16384), 2048 layers
  Maximum Layered 2D Texture Size, (num) layers  2D=(16384, 16384), 2048 layers
  Total amount of constant memory:               65536 bytes
  Total amount of shared memory per block:       49152 bytes
  Total number of registers available per block: 65536
  Warp size:                                     32
  Maximum number of threads per multiprocessor:  2048
  Maximum number of threads per block:           1024
  Max dimension size of a thread block (x,y,z): (1024, 1024, 64)
  Max dimension size of a grid size    (x,y,z): (2147483647, 65535, 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:                        Disabled
  Device supports Unified Addressing (UVA):      Yes
  Device PCI Domain ID / Bus ID / location ID:   0 / 130 / 0
  Compute Mode:
     < Default (multiple host threads can use ::cudaSetDevice() with device simultaneously) >
> Peer access from GeForce GTX TITAN X (GPU0) -> GeForce GTX TITAN X (GPU1) : Yes
> Peer access from GeForce GTX TITAN X (GPU0) -> GeForce GTX TITAN X (GPU2) : No
> Peer access from GeForce GTX TITAN X (GPU0) -> GeForce GTX TITAN X (GPU3) : No
> Peer access from GeForce GTX TITAN X (GPU1) -> GeForce GTX TITAN X (GPU0) : Yes
> Peer access from GeForce GTX TITAN X (GPU1) -> GeForce GTX TITAN X (GPU2) : No
> Peer access from GeForce GTX TITAN X (GPU1) -> GeForce GTX TITAN X (GPU3) : No
> Peer access from GeForce GTX TITAN X (GPU2) -> GeForce GTX TITAN X (GPU0) : No
> Peer access from GeForce GTX TITAN X (GPU2) -> GeForce GTX TITAN X (GPU1) : No
> Peer access from GeForce GTX TITAN X (GPU2) -> GeForce GTX TITAN X (GPU3) : Yes
> Peer access from GeForce GTX TITAN X (GPU3) -> GeForce GTX TITAN X (GPU0) : No
> Peer access from GeForce GTX TITAN X (GPU3) -> GeForce GTX TITAN X (GPU1) : No
> Peer access from GeForce GTX TITAN X (GPU3) -> GeForce GTX TITAN X (GPU2) : Yes

deviceQuery, CUDA Driver = CUDART, CUDA Driver Version = 7.5, CUDA Runtime Version = 7.5, NumDevs = 4, Device0 = GeForce GTX TITAN X, Device1 = GeForce GTX TITAN X, Device2 = GeForce GTX TITAN X, Device3 = GeForce GTX TITAN X
Result = PASS
root@gpu3:~/cuda/NVIDIA_CUDA-7.5_Samples#

( Polesz v | 2016. 05. 21., szo – 16:10 )

Fájdítsad csak a szívem, jó van ;-)

--
A főnököm mindig megtartja amit ígér, ha pénzt ígér azt is!

( Hunger | 2016. 05. 24., k – 11:07 )

Drága TITAN X kártyákat rakni, amikor jönnek a sokkal gyorsabb 1080 kártyák és ráadásul olcsóbban... :P

( Elbandi v | 2016. 05. 26., cs – 20:46 )

jojo, de mennyi x11 shitcoint lehet ezzel banyaszni? :)

--
A vegtelen ciklus is vegeter egyszer, csak kelloen eros hardver kell hozza!