Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

HPE unveils The Machine, a single-memory computer with 160 terabytes of memory

venturebeat.com

Post reply on HN
Print view View original

51–57 of 57 posts

Re: HPE unveils The Machine, a single-memory computer with 160 terabytes of memory

#51

Post by eveningcoffee »

closeparen wrote: post #47
eveningcoffee wrote: post #14

I am not sure if I should be impressed until they reveal more details. 160 TB over 40 nodes is 4 TB per node, which assuming 512 GB dimms requires only 8 dimms (4 per socket) or with 256 GB dimms 16 dimms (8 per socket). How fast is the interconnect? 100Gb/s? So far it sounds like an common high memory HPC cluster unit with really unknown technical parameters.

Isn't the idea that a single process can address all 160TB of memory as if it were local? Of course you can cobble together that much memory when you're programming a distributed system of communicating processes. The interesting part would be programming it as if for one computer.

As far I understand, this memory would be not local to any of the processors - all of them access it through shared bus (fabric as they call it) and it appears to be handled rather as a weird (their words) disk device than as a memory.

I did not find information about the bandwidth or latency of such architecture.

Re: HPE unveils The Machine, a single-memory computer with 160 terabytes of memory

#52

Post by eveningcoffee »

rbanffy wrote: post #40
eveningcoffee wrote: post #14

I am not sure if I should be impressed until they reveal more details. 160 TB over 40 nodes is 4 TB per node, which assuming 512 GB dimms requires only 8 dimms (4 per socket) or with 256 GB dimms 16 dimms (8 per socket). How fast is the interconnect? 100Gb/s? So far it sounds like an common high memory HPC cluster unit with really unknown technical parameters.

Well... Consider https://www.supermicro.nl/products/system/7U/7088/SYS-7088B-... This 7U box can have 24TB on a single 192-core/384-thread node using 128GB DIMMs. At 7U, you can fit 5 of them on 40u of rack space (assuming you can deliver power and get rid of the heat) and deal with far less inter-node communication and CPUs that can run rings around the best ARM-based ones. You can also pack 8 GPUs or your favorite…

The interesting part seems to be their NGMI (next -generation memory interface) that as far I understand acts as a kind of memory bus and each processor will use it more like a disk device (with special functionality like support for atomic operations etc).

Unfortunately I did not find any performance information about it.

Re: HPE unveils The Machine, a single-memory computer with 160 terabytes of memory

#53

Post by qb45 »

bitL wrote: post #26

How does the Machine recover from software errors? If it has only persistent RAM, then when some important program goes bonkers (it always goes), there is no luxury of pressing the reset button to get back to a pristine state.

Taking into account the possibility of memory corruption, I think ultimately they won't get away without some sort of checkpointing to external storage.

To actually take advantage of persistent RAM and have fast restarts with no rollback, I bet early solutions will just partition the RAM into "bonkers-prone software" and "data" parts, with reboots involving a complete wipe of the former. Then somebody will submit Linux patches to keep some application or kernel data in the data part and hell knows where it goes from there.

And BTW, the announcement doesn't say they already have persistent RAM.

Re: HPE unveils The Machine, a single-memory computer with 160 terabytes of memory

#54

Post by rwmj »

closeparen wrote: post #47
eveningcoffee wrote: post #14

I am not sure if I should be impressed until they reveal more details. 160 TB over 40 nodes is 4 TB per node, which assuming 512 GB dimms requires only 8 dimms (4 per socket) or with 256 GB dimms 16 dimms (8 per socket). How fast is the interconnect? 100Gb/s? So far it sounds like an common high memory HPC cluster unit with really unknown technical parameters.

Isn't the idea that a single process can address all 160TB of memory as if it were local? Of course you can cobble together that much memory when you're programming a distributed system of communicating processes. The interesting part would be programming it as if for one computer.

Distributed shared memory on commodity hardware/networks is a long solved problem. I was using TreadMarks back in 1994. Making it perform well, on the other hand, is a real challenge.

Re: HPE unveils The Machine, a single-memory computer with 160 terabytes of memory

#55

Post by jhiska »

Neat press release. Bombastic, eye-catching, has people asking what it is.

But the product is just a high memory HPC cluster unit, 4TB per node. It's not "revolutionary", it won't "change everything", it's not a "technological breakthrough".

TL;DR: It's press-bait.

Re: HPE unveils The Machine, a single-memory computer with 160 terabytes of memory

#56

Post by krylon »

cdelsolar wrote: post #41

This is funny, because in 100 years, computers with 100 yottabytes of memory will be standard, and they'd be laughing at a headline like this one.

Or they will let out a nostalgic sigh as they think about those simpler days where you could get useful work done on 4 GB of RAM... ;-)

Re: HPE unveils The Machine, a single-memory computer with 160 terabytes of memory

#57

Post by lawpoop »

bitL wrote: post #50
lawpoop wrote: post #45

Earlier quoted context omitted.

My guess is that there would be a microkernel service that is the core OS, like the BIOS, and it could be instructed to actively wipe the memory and reload the boot files when the machine freezes

There can be bug in a microkernel service (and as it is distributed, it is actually guaranteed it will crash unexpectedly at some point)

Well I guess it's a disposable computer then. Use until it crashes.
Post reply on HN