Intel Xeon D-1500 Series Discussion

icrf

New Member
Aug 5, 2015
7
1
3
38
What is the difference between the D-1540, D-1541, and D-1548? Let's ignore the 100 MHz the 1541 has, and the SR-IOV issues with the 1540. I've read the front page posts and see that 1541 is a storage accelerated part, and the 1548 is a network accelerated part, but I'm still fuzzy on what that means. They have support for SPDK and DPDK, respectively, but those look like software SDKs. Is there specific hardware on-chip that only those SKUs have? Do they pass through to virtualized guests? What is the software support for those SDKs in the real world? What features in what form would I have to be using to take advantage of them?

For example, the storage slide lists "data protection" with what looks like a parity calculation. What filesystem drivers would make use of this? Would it need to be an linux MD array, or could it be something like zfs/btrfs? I'm currently using the latter in RAID10 (or whatever they're calling it) until RAID6 support firms up, which could maybe use faster parity. The filesystems do checksumming, too, so does that fall under the listed "data integrity" category? Or since I'm not using SSDs for my storage array, none of those things matter, since the hardware will always be the bottleneck and I shouldn't spend any extra money on these storage accelerators?

The network accelerated parts support SSL, so faster HTTPS and OpenVPN connections through the OpenSSL library. If I wanted to use something like IPSEC instead, does that get no speedup? Does it depend on the particular library I'm using? How much hardware is needed for a full gigabit of encrypted throughput? Ten gigabits? I'm one of those lucky Chattanooga residents, so these are not theoretical someday maybe connection possibilities, they're a mere phone call away.

My concern is because I'm thinking about this in terms of devices like the Netgear R7000 router. Running stock firmware, IPv4 NAT throughput is something like 450 Mbps. Running DD-WRT, throughput drops to 360 Mbps, because the stock firmware was offloading to a NAT co-processor, but its interface isn't documented so the open source firmware can't use it. I feel like all these accelerator SDK abilities could just be lost and useless if the major software packages we all want to use don't support it for whatever reason. When CPUs get new instructions, there's a lag time before implementation, and if the CPUs with the new instructions don't sell in sufficient volume, they may never get supported. If there are specific hardware features required for SPDK/DPDK support, will they sell in enough volume for developers to bother?
 

AmshTemp

New Member
May 28, 2015
18
0
1
40
Be careful ! They are "4Rx4".
In Xeon-D, you have 4 slots connected to 2 channels. Each channel has a max of 4 ranks.

These memory sticks are 4 ranks, which means you can install 1 per channel, which means you can install only 2 of them. ( =64GB )

If you want to be able to install 4 ( =128GB ), get a 2 rank, they are available online.
 

EluRex

Active Member
Apr 28, 2015
209
70
28
Los Angeles, CA
I don't know how Intel E3-12xx v5 & E5-16xx v3 can be more attractive than the new xeon-d with 16 core... its unbelievable.... and the 15x8 with quickassist really targeting firewall/router big time... but only if they can bring the tdp down to 20w
 

pyro_

Active Member
Oct 4, 2013
726
161
43
For the 16xx I could see situations where you needed more pcie lanes than these would provide. Also look at clock speeds for single threaded apps which there are still a bunch out there they prefer the high speed cores to having more of them
 

Markus

Member
Oct 25, 2015
78
19
8
I think, I'll go for the 16 Core - Board. Just returned the SM 1540 Board and waiting for the money.

Any suggestions, how much the 16 Core could be?
Regards
Markus
 
  • Like
Reactions: gigatexal

EluRex

Active Member
Apr 28, 2015
209
70
28
Los Angeles, CA
Yes. That is why I find strange that they claim it is not supported.
I think SM has just disabled the option. But now with this custom BIOS one should be able to do it.

Hence the request to you or Jerry or whoever also made it work for the full steps so that I can possibly try it on this custom 1.0b
@jonaspaulo check https://forums.servethehome.com/ind...oes-not-work-i350-work.7309/page-2#post-66606

It is confirmed that sr-iov will work on intel i350 card with the custom bios 1.0b from Supermicro
 

Abhiu3

New Member
Nov 11, 2015
3
0
1
34
I have the 5028 case. Quiet to me is basically hear nothing. That is how my office PC is. This thing definitely makes some noise but is not crazy loud. I keep mine upstairs behind the TV and the dogs still manage to sleep at night.
 

Davewolfs

Active Member
Aug 6, 2015
337
31
28
Is it confirmed that it's fully reliable? This really sounds more like a late-discovered bug than a conspiracy to take away a feature for no reason.
SM should allow users to RMA their boards for a 1541 replacement.
 

EluRex

Active Member
Apr 28, 2015
209
70
28
Los Angeles, CA
Is it confirmed that it's fully reliable? This really sounds more like a late-discovered bug than a conspiracy to take away a feature for no reason.
I am a believer of the conspiracy theory due to ixgbe driver version 4.0.5, I was able to enable the SR_IOV function on x557(silly me that I didn't do a ping test then!), later it was SM totally disabling it from the BIOS version 1.0.b

SM should allow users to RMA their boards for a 1541 replacement.
Better yet, they can send us the 1541 and we can return the 1540 back to Intel.
 

hjfr

Member
Nov 21, 2013
76
20
8
France
Could someone explain to me what are the SFI/KR/KR4/KX/KX4 interfaces that appear with new Xeon D released last week ?
Example:
- "KR4 interface" is not present for any Xeon D and pentium D.
- "KR interface" is not present for Xeon D-1518 and Pentium D-1507
Consequence ?
I don't found any information about this.



Second question, What size fan to put on the Xeon D heatsink from supermicro motherboard ?
40x40mm, 60x60mm or other ?