I'm sure those SGIers now at HPE will be delighted to see so much being made of the UV.
Oh.
HPE unveils The Machine, a single-memory computer with 160 terabytes of memory
31–40 of 57 posts
Re: HPE unveils The Machine, a single-memory computer with 160 terabytes of memory
#32> The new prototype has 160 TB of shared memory spread across 40 physical nodes, interconnected using a high-performance fabric protocol. So basically something similar to RDMA scaled to 40 nodes, 4 TB RAM per node.
I think the interesting part is the programming model and not the amount of RAM. This computer has no separate storage area. If you want to manipulate data, you can do it in-place instead of reading it into a RAM-like working memory and then writing the result to a disk-like storage.
Re: HPE unveils The Machine, a single-memory computer with 160 terabytes of memory
#33Earlier quoted context omitted.
~100 billions neurons in a human brain I guess. Not sure what 1.6KB per neuron is too close to
This comment currently has a reply ( http://i.imgur.com/N7BZJfu.png ) which shows why I wanted to leave my original post as a "riddle" rather than coming out and saying it. The following "crap" is not relevant to anything, only read it if you want the answer to why 1.6 KB is insufficient for a certain science fiction fantasy which will never, not in ten, a hundred, or a thousand years, become relevant any more than m…
You made a math error:
You can encode about 300 addresses, at 36+8 = 44 bits per item, not 45 addresses, at 36*8 = 288 bits per address.
The bits are additive, because we're storing an address and data, not a byte of data per bit of address.
Re: HPE unveils The Machine, a single-memory computer with 160 terabytes of memory
#34Earlier quoted context omitted.
Maybe just say what you mean, instead of riddles, as part of contributing to the discussion?
~100 billions neurons in a human brain I guess. Not sure what 1.6KB per neuron is too close to
I'd guess that it would be close to the size of the adjacency matrix for the human brain, if it is given that the brain has ~1000 dendrites per neuron.
Re: HPE unveils The Machine, a single-memory computer with 160 terabytes of memory
#35Earlier quoted context omitted.
~100 billions neurons in a human brain I guess. Not sure what 1.6KB per neuron is too close to
This comment currently has a reply ( http://i.imgur.com/N7BZJfu.png ) which shows why I wanted to leave my original post as a "riddle" rather than coming out and saying it. The following "crap" is not relevant to anything, only read it if you want the answer to why 1.6 KB is insufficient for a certain science fiction fantasy which will never, not in ten, a hundred, or a thousand years, become relevant any more than m…
> why I wanted to leave my original post as a "riddle" rather than coming out and saying it.
Because the comment was fundamentally irrelevant? You could post "step up your game" on every single tech submission. It's white noise.
Re: HPE unveils The Machine, a single-memory computer with 160 terabytes of memory
#36Earlier quoted context omitted.
It's a 40 node mesh. Isn't that scale-out?
Let me rephrase rather. a scale out architecture with commodity machines (using Hadoop, kube, mesos etc.) versus an engineered system in hardware. A client purchased a an HP super dome (another highly engineered system) the cost per CPU core, gb ram, tb of storage was horrendous. More than 10x comparable commodity hardware solutions. 8 months later and they hit performance problems, space issues and adding capacity i…
I believe the usecase is needing high bandwidth interconnects, eg, problems with a lot of synchronizations across the dataset.
Re: HPE unveils The Machine, a single-memory computer with 160 terabytes of memory
#37I 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.
"So far it sounds like an common high memory HPC cluster unit with really unknown technical parameters." And really anemic CPUs to boot...
Only real interesting part would be the technical details of their NGMI interconnect.
Only thing that I understood so far is that it is based on FPGA that suggest that it is experimental i.e. no ASIC yet.
Re: HPE unveils The Machine, a single-memory computer with 160 terabytes of memory
#38The Machine should be fine, but if Samaritan comes online, we are doomed!
Re: HPE unveils The Machine, a single-memory computer with 160 terabytes of memory
#39Wasn't the Machine supposed to be a memristor computer? Did they ditch the project?
memristors are unfortunately still vaporware
Re: HPE unveils The Machine, a single-memory computer with 160 terabytes of memory
#40I 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 Xeon Phi card (but each will behave like a cluster node) and 8 NVMe cards and 32 2.5" devices. This is slightly less dense than the HP offering, but you can order 5 of them right now. If you do, tell them I told you to.
If you move it to 256GB DIMMs which, it was pointed out, is probably what HPE is using, you have 240TB per rack.