Re: [PATCH V2 for-next 0/9] Peer-Direct support

2014-11-11 Thread Or Gerlitz
On Tue, Oct 28, 2014 at 8:29 PM, Coffman, Jerrie L jerrie.l.coff...@intel.com wrote: [...] to obtain the source for review. Steps are as follows: Download and extract the latest OFED-3.12-1 release (rc3 in this case) from OpenFabrics.org cd OFED-3.12-1-rc3/SRPMS/ rpm2cpio

Re: [PATCH V2 for-next 0/9] Peer-Direct support

2014-11-11 Thread Coffman, Jerrie L
On Tue, Nov 11, 2014 at 12:44 AM, Or Gerlitz gerlitz...@gmail.com wrote: [...] can you make it easily reviewable? that is, either send as patches to this list or much easier put the relevant piece in public git tree (github?) While it does take some effort to obtain the code, there are

Re: [PATCH V2 for-next 0/9] Peer-Direct support

2014-10-28 Thread Coffman, Jerrie L
On Mon, Oct 27, 2014 at 2:25 PM, Yishai Hadas yishaih@ wrote: Intel people pointed that CCL Direct for Intel Xeon Phi uses this API. See  http://www.spinics.net/lists/linux-rdma/msg21605.html . We are checking with Intel whether the relevant stuff can be shared for some  early

Re: [PATCH V2 for-next 0/9] Peer-Direct support

2014-10-27 Thread Yishai Hadas
On 10/23/2014 8:29 PM, Roland Dreier wrote: On Thu, Oct 23, 2014 at 5:02 AM, Yishai Hadas yish...@mellanox.com wrote: The API defined for Peer-Direct is described in this cover letter. The required implementation for a hardware device to expose memory buffers over Peer-Direct is also detailed

[PATCH V2 for-next 0/9] Peer-Direct support

2014-10-23 Thread Yishai Hadas
The following set of patches implements Peer-Direct support over RDMA stack. Peer-Direct technology allows RDMA operations to directly target memory in external hardware devices, such as GPU cards, SSD based storage, dedicated ASIC accelerators, etc. This technology allows RDMA-based

Re: [PATCH V2 for-next 0/9] Peer-Direct support

2014-10-23 Thread Roland Dreier
On Thu, Oct 23, 2014 at 5:02 AM, Yishai Hadas yish...@mellanox.com wrote: The API defined for Peer-Direct is described in this cover letter. The required implementation for a hardware device to expose memory buffers over Peer-Direct is also detailed in this letter. I don't see how I can