Difference between revisions of "Bricks"
From MonetDB
Jump to navigationJump to searchm |
|||
| Line 48: | Line 48: | ||
|- | |- | ||
! bricks14 | ! bricks14 | ||
| − | | slow || | + | | slow || 2x [[#nVIDIA GeForce GTX Titan|nVIDIA GeForce GTX Titan]] || 6 GiB || |
|- | |- | ||
! bricks15 | ! bricks15 | ||
Revision as of 08:50, 30 May 2016
The bricks are a group of machines in the SciLens cluster with some special hardware items on individual machines, described below.
| 1 TB /ssd (slow/fast) |
Accellerator: GPU / Xeon Phi |
On-card Memory | other | |
|---|---|---|---|---|
| bricks01 | slow | SAS (Thunderbolt): 4x 24x 2 TB = 4x 48 TB = 192 TB | ||
| bricks02 | fast | 1x NVIDIA GeForce GTX Titan X | 12 GiB | |
| bricks03 | fast | |||
| bricks04 | slow | 2x nVIDIA Tesla K20c | 2x 5 GB | |
| bricks05 | fast | |||
| bricks06 | slow | 1x Intel Xeon Phi ([357](?)100 Series: ? cores) | ? GB | |
| bricks07 | fast | |||
| bricks08 | slow | 2x nVIDIA GeForce GTX 680 | 2x 2 GiB | |
| bricks09 | fast | |||
| bricks10 | slow | 2x Intel Xeon Phi ([357](?)100 Series: ? cores) | 2x ? GB | |
| bricks11 | fast | |||
| bricks12 | slow | 1x nVIDIA Tesla K20c | 5 GB | |
| bricks13 | fast | |||
| bricks14 | slow | 2x nVIDIA GeForce GTX Titan | 6 GiB | |
| bricks15 | fast | |||
| bricks16 | slow | 2x AMD/ATI Radeon HD 7900(?) (2x ? ) | 2x ?GB |
Note the difference between space listings in GB (10^9 bytes) and in GiB (2^30 bytes).
You might also want to have a look at the common hardware baseline for all the bricks,
Coprocessor card specifications
nVIDIA GeForce GTX Titan X
A GM200 Maxwell-family architecture GPU discrete card on the PCIe bus.
Relevant deviceQuery output:
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 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
nVIDIA GeForce GTX Titan
A GK110 Kepler-family architecture GPU discrete card on the PCIe bus.
relevant deviceQuery output:
CUDA Capability Major/Minor version number: 3.5 Total amount of global memory: 6144 MBytes (6442254336 bytes) (14) Multiprocessors, (192) CUDA Cores/MP: 2688 CUDA Cores GPU Clock rate: 876 MHz (0.88 GHz) Memory Clock rate: 3004 Mhz Memory Bus Width: 384-bit L2 Cache Size: 1572864 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 1 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
nVIDIA Tesla K20c
A GK110GL Kepler-family architecture GPU discrete card on the PCIe bus.
Relevant deviceQuery output:
CUDA Capability Major/Minor version number: 3.5 Total amount of global memory: 4800 MBytes (5032706048 bytes) (13) Multiprocessors, (192) CUDA Cores/MP: 2496 CUDA Cores GPU Clock rate: 706 MHz (0.71 GHz) Memory Clock rate: 2600 Mhz Memory Bus Width: 320-bit L2 Cache Size: 1310720 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: Enabled Device supports Unified Addressing (UVA): Yes
nVIDIA GeForce GTX 680
A GK104 Kepler-family architecture GPU discrete card on the PCIe bus.
Can't run deviceQuery on this one until CUDA is properly installed on bricks08, so consult the [on nVIDIA's website].
