Stack Overflow
Stack Overflow

Questions tagged [gpudirect]

Tag for NVIDIA GPUDirect

Using GPUDirect, multiple GPUs, third party network adapters, solid-state drives (SSDs) and other devices can directly read and write CUDA host and device memory, eliminating unnecessary memory copies, dramatically lowering CPU overhead, and reducing latency, resulting in significant performance improvements in data transfer times for applications running on NVIDIA Tesla™ and Quadro™ products.

Resources:

  1. NVIDIA GPUDirect
  2. Documentation
16 questions
12
votes
3 answers

Does AMD's OpenCL offer something similar to CUDA's GPUDirect?

NVIDIA offers GPUDirect to reduce memory transfer overheads. I'm wondering if there is a similar concept for AMD/ATI? Specifically: 1) Do AMD GPUs avoid the second memory transfer when interfacing with network cards, as described here. In case…
arrayfire
  • 1,744
  • 12
  • 19
10
votes
1 answer

GPUDirect RDMA transfer from GPU to remote host

Scenario: I have two machines, a client and a server, connected with Infiniband. The server machine has an NVIDIA Fermi GPU, but the client machine has no GPU. I have an application running on the GPU machine that uses the GPU for some calculations.…
DaoWen
  • 32,589
  • 6
  • 74
  • 101
8
votes
1 answer

Does the nVidia RDMA GPUDirect always operate only physical addresses (in physical address space of the CPU)?

As we know: http://en.wikipedia.org/wiki/IOMMU#Advantages Peripheral memory paging can be supported by an IOMMU. A peripheral using the PCI-SIG PCIe Address Translation Services (ATS) Page Request Interface (PRI) extension can detect and signal…
Alex
  • 12,578
  • 15
  • 99
  • 195
4
votes
1 answer

How to use GPUDirect RDMA with Infiniband

I have two machines. There are multiple Tesla cards on each machine. There is also an InfiniBand card on each machine. I want to communicate between GPU cards on different machines through InfiniBand. Just point to point unicast would be fine. I…
Hot.PxL
  • 1,902
  • 1
  • 17
  • 30
2
votes
1 answer

RDMA Read protection for local memory operations

I have the following scenario: My server allocates a buffer of 1MB, which is periodically updated and written to (about every 50ms). The client is connected to the the server via Infiniband and periodically reads that buffer via RDMA Read…
hey0
  • 43
  • 6
2
votes
1 answer

Setting up GPUDirect for infiniband

I try to setup GPUDirect to use infiniband verbs rdma calls directly on device memory without the need to use cudaMemcpy. I have 2 machines with nvidia k80 gpu cards each with driver version 367.27. CUDA8 is installed and Mellanox OFED 3.4 Also the…
kusterl
  • 29
  • 5
2
votes
1 answer

Can I use in CUDA atomic-operations on remote GPU-RAM over GPUDirect 2.0 P2P?

For example i can use CUDA atomic operations atomicAdd(ptr, val), atomicCAS(ptr, old, new), ... on its global memory (GPU-RAM). With CUDA 6.5. But can I use these atomic-operations for the remote global memory over GPUDirect 2.0 P2P?
Alex
  • 12,578
  • 15
  • 99
  • 195
2
votes
1 answer

How does GPUDirect enforce isolation on a shared device

I have been reading here https://developer.nvidia.com/gpudirect about GPUDirect, In there example there is a network card attached to the PCIe together with two GPU's and a CPU. How is isolation enforced between all clients trying to access the…
yonigo
  • 987
  • 1
  • 15
  • 30
1
vote
1 answer

RDMA read and write data placement/visibility semantics

I am trying to get more details on the RDMA read and write semantics (especially data placement semantics) and I would like to confirm my understanding with the experts here. RDMA read : Would the data be available/seen in the local buffer, once…
user718134
  • 13
  • 2
1
vote
0 answers

glTexSubImage2D() and glGetTextureImageEXT() used instead of GPUDirect

My setup: NVIDIA Quadro p6000 (used for GPUDirect) AJA video card (SDI feed from camera and SDI output to the TV) I am trying to figure out what is the purpose of GPUDirect (in my specific case) if I can achieve the same amount of copying and the…
Bojan Lovrovic
  • 11
  • 4
1
vote
1 answer

Nvidia GPUDirect and camera capturing to GPU

I have a USB3 camera, and I need to have the captured images to be loaded into DirectX texture. Currently I'm just doing it in my code in the user mode - grab images and upload them to GPU, which is, of cause, certain overhead on CPU and delay of…
Michael Gopshtein
  • 330
  • 1
  • 11
1
vote
1 answer

Can I use GPUDirect v2 Peer-to-Peer communication between two Quadro K1100M or two GeForce GT 745M?

Can I use GPUDirect v2 - Peer-to-Peer communication on a single PCIe-Bus?: between two: Mobile nVidia Quadro K1100M between two: Mobile nVidia GeForce GT 745M
Alex
  • 12,578
  • 15
  • 99
  • 195
1
vote
3 answers

CUDA: GPUDirect on GeForce GTX 690

The GeForce GTX 690 (from vendors like Zotac and EVGA) can be used for CUDA programming, much like a Tesla K10. Question: Does the GeForce GTX 690 support GPUDirect? Specifically: If I were to use two GTX 690 cards, I would have 4 GPUs (two GPUs…
Prateeksha Shenoy
  • 21
  • 2
0
votes
0 answers

RDMA support GPUDirect feature

NVIDIA GPUs want to GPUDirect RDMA feature. Must it use hardware RDMA NIC by Mellanox like ConnectX-5 NIC, or I can use other RDMA by other companies and adapt it to support GPUDirect feature. If so, what do I need to install? Now, I make some RDMA…
xiaobin
  • 1
  • 2
0
votes
0 answers

GPUDirect RDMA out of range pin address by Quadro p620

I want to implement FPGA-GPU RDMA by nvidia quadro p620. Also, I used common PCIe BAR resources(BAR0 - BAR1 - BAR2) for FPGA registers and other chunk controllers handling which is independent from RDMA in my custom driver. PCIe managements are OK…
SkyCyborg
  • 1
  • 2
1
2