Servers
HP previews ProLiant Gen8 servers
You can look at HP's new ProLiant Gen8 servers, but you can't touch. At the company's Global Partner Conference in Las Vegas this week, HP previewed some of the forthcoming machines' capabilities, but – much to the chagrin of hardware enthusiasts – didn't talk about the processors, system boards, and other "slots and watts" …
This topic is closed for new posts.
Nooooooo!
Which whale-song-listening, incense-burning, marketeer came up with those nasty fronts!?!
I agree in a way
In that it doesn't look handsome.
Then I realised it'll be sat in datacentre, and you won't be staring at it, so it doesn't matter.
Fronts
Eww, looks like they got them second hand from Dell; hopefully an optional extra that they don't have as standard.
RE: I agree in a way
"....Then I realised it'll be sat in datacentre..." Agreed, rack-it-once-and-manage-remotely makes a "pretty" front pointless. I could understand it on maybe office versions of the ML towers, otherwise it just looks unprofessional. The existing G7s' fronts look like they are engineered for maximum and efficient airflow, which is important. I want a box that looks like it has been engineered to meet a business requirement, not to give some hifi afficianado wet dreams. How much of what my company will be paying for these is being wasted on "prettiness"? If it's an optional extra I can guarantee it's one we will be knocking off any orders.
Since HP Gen8 is targeting Cisco UCS, it would make sense for HP to include a memory solution to match (or better) Cisco's "Catalina ASIC" based "ASIC-on-motherboard" approach (compared to Netlist HyperCloud/LRDIMM approach of ASIC-on-memory-module).
If "HP smart memory" is actually HyperCloud - it should allow them considerably latency improvement over the Cisco UCS solution.
So in summary if you compare the latency advantages for Netlist:
- LRDIMMs have a "5 ns latency penalty" compared to RDIMMs (from Inphi LRDIMM blog)
- CSCO UCS has a "6 ns latency penalty" compared to RDIMMs.
- NLST HyperCloud have similar latency as RDIMMs (a huge advantage) and have a rather significant "4 clock latency improvement" over the LRDIMM (quote from Netlist Craig-Hallum conference)
The author's earlier article on HyperCloud vs. Cisco UCS is the first link below.
Netlist and Cisco UCS:
http://www.theregister.co.uk/2009/11/11/netlist_hypercloud_memory/
Netlist goes virtual and dense with server memory
So much for that Cisco UCS memory advantage
By Timothy Prickett Morgan
Posted in Servers, 11th November 2009 18:01 GMT
Suggestion that Cisco UCS has a "6 ns latency penalty" compared to RDIMMs:
http://knudt.net/vblog/post/2009/10/05/UCS-Boot-Camp-Day-1.aspx
UCS Boot Camp - Day 1
by knudt October 5 2009 23:13
quote:
----
...without affecting bus speed and only incurring minimal additional latency (6 ns)
----
http://messages.finance.yahoo.com/Stocks_%28A_to_Z%29/Stocks_N/threadview?m=te&bn=51443&tid=36202&mid=36389&tof=1&frt=2#36389
Re: Let the truth be revealed on IPHI CC .. CSCO UCS and LRDIMMs 6-Nov-11 11:31 am
The memory thread above now includes an excellent analysis of what "HP smart memory" with it's "faster speed (25%)" and DRAM error "logging" capability probably means.
http://messages.finance.yahoo.com/Stocks_%28A_to_Z%29/Stocks_N/threadview?m=te&bn=51443&tid=44434&mid=44509&tof=21&frt=2#44509
Re: HP Gen8 answer to Cisco UCS .. "HP Smart Memory" = HyperCloud ? 15-Feb-12 11:39 am
The question now is if ALL of the "HP smart memory" will have the "faster speed (25%)" capability, or if HP will be supplying this in two varieties (to mirror the RDIMM and NLST HyperCloud types of memory).
Or whether HP will be going with a unified memory - which would allow simpler inventory and allow customers who buy smaller amounts of memory to later scale up and still get the "faster speed (25%)" for the "high memory loading" applications.
That's enough shilling, netlistpost
I have zapped your account.
Our forums are not a promotional vehicle for your company. And what's with the anonymity - this is completely inappropriate considering your game plan.
Buy some advertising or engage properly with our readers.
Pity about the look
Too bad about that ugly front fascia. I always thought Dell did that mostly to hide their poorly engineered hardware. And who the heck has the time to unlock a faceplate every time they need to check something, and keep track of all the keys?
Perhaps this is the beginning of the "Megging" of the company. Ugh.
Smart Drive
So this is different to the red lights on bad drives green lights on good drives?
Re: Smart Drive
They didn't actually explain it, but having replaced a fair number of dead ProLiant drives in my time--love that RAID 6--I couldn't quite grasp what the problem is, either.
Re: Re: Smart Drive
You know that raid-6 has lot of issues, right? The data might be corrupted, without the hardware/OS knowing it.
Re: Re: Re: Smart Drive
Kebbie, please leave off with the very outdated FUD, we've seen enough of it in your fawning appraisals of ZFS. Unless you can post real, documented evidence of issues with RAID6, and not just your usual marketeer links which are all statistical gobbleydegook with no actual real World examples, on yer bike.
HP is a huge IBM copier
Is everything from HP going to be smart______? Not what IBM's marketing is Smarter Planet, Smarter computing, etc....?
Re: HP is a huge IBM copier
I think you'll find such items as the SmartArray cards go back to even before the Compaq buy, and considerably earlier than any recent pieces of IBM fluff.
Re: Re: HP is a huge IBM copier
I seem to remember that the SystemPro/ProLiant had something called SmartStart in the early nineties that had customers driving me crazy with questions about why we did not have it. Maybe IBM copied ProLiant due to their lack of history in the x86 server world.
Let's hope that this isn't how customer meetings go from now on after this Gen8 announcement...
If you can't tolerate extreme sarcasm, don't watch...
http://www.youtube.com/watch?v=3CnYk2cqW_c
This topic is closed for new posts.
