Hi everyone! So I'm pretty new and noob in Raspberry Pi and Boinc stuff so don't judge me please.
So, my friends gave me an Raspberry Pi B+ and I try to start Einstein there with Boinc. I know It's not fast and It's old etc. but in this point I don't really care. Anyway, I can add it but it never start download packages and anything, just sitting there. I tried Seti and that is working perfect. I don't know what I'm doing wrong? Can someone help me? Thanks!
And sorry if someone have already asked this and I ask it again but like you can see, there is ton of posts on this topic. So...
So, my friends gave me an Raspberry Pi B+ and I try to start Einstein there with Boinc. I know It's not fast and It's old etc. but in this point I don't really care. Anyway, I can add it but it never start download packages and anything, just sitting there. I tried Seti and that is working perfect. I don't know what I'm doing wrong? Can someone help me
The BRP4 science app from the project requires a Pi2B at a minimum. It will also work on the 3B and 3B+ but not the older ones. The B+ has an ARM v6 processor, the later Pis have an ARM v7 or ARM v8 processor. The app needs v7 or later.
Added a couple more Pi3 model B+ to the bramble. Its now up to 12 compute nodes. I suppose I should reuse the Pi3 model B’s as well but that means I will have to get some more network cables. I have some spare power cables and USB chargers I can use.
Earlier this month Cambricon announced the company’s first AI accelerator for the data center in a bid to get a piece of the pie from a booming AI market; a market currently largely dominated by companies such as Nvidia and Intel. The startup has only been around since 2016 but has since managed to ship its IPs in millions of devices thanks in part to a large push from the Chinese government. Cambricon’s first IP, the 1A, has been shipping with HiSilicon’s Kirin 970 since late last year.
The new chip is called the MLU100 and is designed for data center workloads. Though we do not have architectural details yet, Cambricon told us that the MLU100 can be thought of as a scaled-up version of their mobile IPs – in both computational power and power consumption. The chip is a result of a multi-year development effort which includes a large set of changes and improvement over their mobile design.
MLU100 (Cambricon)In case you were wondering, MLU stands for Machine Learning Unit. The MLU100 supports Cambricon’s most recent architecture which is still the MLUv01. The chip is fabricated on TSMC’s 16nm process and operates at a base frequency of 1 GHz which they refer to as balanced mode. There is also a high-performance mode with a frequency of 1.3 GHz, although the performance efficiency is slightly worsened.
In balanced mode, the chip has a theoretical peak performance of 128 trillion fixed-point (8-bit int) operations per second while achieving 166.4 TOPS in high-performance mode. In terms of half-precision floating point (16-bit), the chip is capable of 64 TFLOPS at 1 GHz and 83.2 TFLOPS in high-performance mode. This is all done within an 80 (balance) and 110 (high-perf) Watts power envelope. Cambricon says that the chip does well with all popular machine learning algorithms through support from their NeuWare software platform which supports all of the popular development frameworks (TensorFlow, Caffe, MXnet, Android NN, etc..).
Accelerator Card
An accelerator card based on the MLU100 has also been announced. The x16 PCIe card comes in two variations – a 16 GB and a 32 GB of DDR4 – with a memory bandwidth of 102.4 GB/s. Cambricon has already partnered up with Lenovo to offer the cards as an optional add-on to their ThinkSystem SR650 servers. The SR650 comes with up to two Xeon Scalable CPUs with up to 56 cores and 3 TiB of memory as well as up to two MLU100 accelerator cards.
I've ordered a Bitscope Blade Rack 20 (link here) so I can stuff all of my Pi3's into 1 box. Hopefully it and the power supply will arrive next week. They recommended a 24v LED lighting transformer rated at 200 watts to power it all.
I've ordered a Bitscope Blade Rack 20 (link here) so I can stuff all of my Pi3's into 1 box. Hopefully it and the power supply will arrive next week. They recommended a 24v LED lighting transformer rated at 200 watts to power it all.
The bits arrived. I also ordered 8 Pi3 model B+ to take the cluster up to 20 nodes. First problem is my existing Pi’s all have heatsinks. There is no room for a heatsink in there so I got the 8 new ones going in the rack so far. Rather than use a Stanley knife to prise the heatsinks off I might just order more Pi’s to fill the rack and then I can finish this build.
The Pi’s in the rack have not had any invalids yet but I have quite a few for the Pi’s using USB chargers, so i put that down to a much better power supply. Pics up on my blog of the build so far.
They are sitting out at the moment. When I get the remaining Pi’s I can assemble the rack parts. It has clear plastic panels on the front and rear with holes in the back for the lan cables. There are also 4 small 30mm fans that go on the back panel.
Temperatures have been 70 degrees C on them when crunching due to the small amount of room between the Duo and the Pi. By contrast my Pi^4 case had 41 degrees when crunching. I think when the rack is assembled they will be even hotter.
Hi everyone! So I'm pretty
)
Hi everyone! So I'm pretty new and noob in Raspberry Pi and Boinc stuff so don't judge me please.
So, my friends gave me an Raspberry Pi B+ and I try to start Einstein there with Boinc. I know It's not fast and It's old etc. but in this point I don't really care. Anyway, I can add it but it never start download packages and anything, just sitting there. I tried Seti and that is working perfect. I don't know what I'm doing wrong? Can someone help me? Thanks!
And sorry if someone have already asked this and I ask it again but like you can see, there is ton of posts on this topic. So...
Marco Buttiglieri wrote:So,
)
The BRP4 science app from the project requires a Pi2B at a minimum. It will also work on the 3B and 3B+ but not the older ones. The B+ has an ARM v6 processor, the later Pis have an ARM v7 or ARM v8 processor. The app needs v7 or later.
MarksRpiCluster
Oh thats the reason! Thank
)
Oh thats the reason! Thank you, then I should buy a newer one!
Marco Buttiglieri wrote:Oh
)
Or try running GoofyX NCI units on this one? http://nci.goofyxgridathome.net/
Then get a new one for Einstein.
Added a couple more Pi3 model
)
Added a couple more Pi3 model B+ to the bramble. Its now up to 12 compute nodes. I suppose I should reuse the Pi3 model B’s as well but that means I will have to get some more network cables. I have some spare power cables and USB chargers I can use.
MarksRpiCluster
https://fuse.wikichip.org/new
)
https://fuse.wikichip.org/news/1297/cambricon-reaches-for-the-cloud-with-a-custom-ai-accelerator-talks-7nm-ips/
Cambricon Reaches for the Cloud With a Custom AI Accelerator, Talks 7nm IPs
Earlier this month Cambricon announced the company’s first AI accelerator for the data center in a bid to get a piece of the pie from a booming AI market; a market currently largely dominated by companies such as Nvidia and Intel. The startup has only been around since 2016 but has since managed to ship its IPs in millions of devices thanks in part to a large push from the Chinese government. Cambricon’s first IP, the 1A, has been shipping with HiSilicon’s Kirin 970 since late last year.
The new chip is called the MLU100 and is designed for data center workloads. Though we do not have architectural details yet, Cambricon told us that the MLU100 can be thought of as a scaled-up version of their mobile IPs – in both computational power and power consumption. The chip is a result of a multi-year development effort which includes a large set of changes and improvement over their mobile design.
In balanced mode, the chip has a theoretical peak performance of 128 trillion fixed-point (8-bit int) operations per second while achieving 166.4 TOPS in high-performance mode. In terms of half-precision floating point (16-bit), the chip is capable of 64 TFLOPS at 1 GHz and 83.2 TFLOPS in high-performance mode. This is all done within an 80 (balance) and 110 (high-perf) Watts power envelope. Cambricon says that the chip does well with all popular machine learning algorithms through support from their NeuWare software platform which supports all of the popular development frameworks (TensorFlow, Caffe, MXnet, Android NN, etc..).
Accelerator Card
An accelerator card based on the MLU100 has also been announced. The x16 PCIe card comes in two variations – a 16 GB and a 32 GB of DDR4 – with a memory bandwidth of 102.4 GB/s. Cambricon has already partnered up with Lenovo to offer the cards as an optional add-on to their ThinkSystem SR650 servers. The SR650 comes with up to two Xeon Scalable CPUs with up to 56 cores and 3 TiB of memory as well as up to two MLU100 accelerator cards.
I've ordered a Bitscope Blade
)
I've ordered a Bitscope Blade Rack 20 (link here) so I can stuff all of my Pi3's into 1 box. Hopefully it and the power supply will arrive next week. They recommended a 24v LED lighting transformer rated at 200 watts to power it all.
MarksRpiCluster
PorkyPies wrote:I've ordered
)
The bits arrived. I also ordered 8 Pi3 model B+ to take the cluster up to 20 nodes. First problem is my existing Pi’s all have heatsinks. There is no room for a heatsink in there so I got the 8 new ones going in the rack so far. Rather than use a Stanley knife to prise the heatsinks off I might just order more Pi’s to fill the rack and then I can finish this build.
The Pi’s in the rack have not had any invalids yet but I have quite a few for the Pi’s using USB chargers, so i put that down to a much better power supply. Pics up on my blog of the build so far.
MarksRpiCluster
Looks nice. How do you ensure
)
Looks nice. How do you ensure cooling?
Neko wrote:Looks nice. How do
)
They are sitting out at the moment. When I get the remaining Pi’s I can assemble the rack parts. It has clear plastic panels on the front and rear with holes in the back for the lan cables. There are also 4 small 30mm fans that go on the back panel.
Temperatures have been 70 degrees C on them when crunching due to the small amount of room between the Duo and the Pi. By contrast my Pi^4 case had 41 degrees when crunching. I think when the rack is assembled they will be even hotter.
MarksRpiCluster