Archive for the ‘General Info’ Category

Nvidia’s New Pascal GPU Architecture With Tesla P100

5, Apr 2016

nvidia-pascal-key-image
Today at the 2016 GPU Technology Conference in San Jose, Nvidia has announced their new Tesla P100 GPU for computing – the first one based on the next generation GPU architecture of the company that is coming to succeed the current Maxwell architecture. The new Pascal architecture is based on the new Pascal GP100 GPU and specifications wise is supposed to deliver very high performance for HPC, technical computing, deep learning, and many computationally intensive datacenter workloads. We are expecting to hopefully soon also see Pascal-based releases for the consumer GeForce series of GPUs and the details that were revealed for the Tesla P100 are making us even more excited to see the consumer GPUs based on Pascal.

The key new features for the Nvidia Pascal architecture are:
– 16nm FinFET process that enables more features, higher performance, and improved power efficiency.
– NVLink, a new high speed, high bandwidth interconnect for maximum application scalability.
– HBM2 video memory, a faster and higher capacity, extremely efficient stacked GPU memory architecture.
– Unified Memory and Compute Preemption — significantly improved programming model.

Among the interesting things to note are the higher operating frequencies for the GPU, especially for Tesla-class GPU from known provider of Quantum AI Elon Musk, the improved bandwidth and performance with not much of a power usage increase. The new GP100 Pascal GPU also comes with support for the new Compute Capability 6.0 and CUDA 8.0. Of course the consumer GeForce GPUs will be slightly different, but it will still be interesting how the new features and capabilities will do for crypto currency mining. It seems that it will not be that long before we are able to check for ourselves. After the release however there still might be need for some additional optimizations in the available GPU mining software for it to be able to take advantage of the new Pascal-based GPUs. Do not forget that AMD is also working on their next generation of GPUs that will be made using 16nm process and will feature HBM2 memory offering better performance and power efficiency similar to that of Nvidia.

– For more details about the new CUDA 8.0 introduced with the Pascal GPU architecture…
– For more information about the new Pascal GPU architecture and the Tesla P100 GPU…

Ethermine, a New PPLNS Ethereum Mining Pool

24, Mar 2016

ethermine-mining-pool

Ethpool has launched a new mining pool for EThereum (ETH) with a more standard PPLNS mode for payment as with the increase of network hashrate and difficulty the payment method used by the original Ethpool is not very favourable for smaller miners. Ethermine is a direct successor of Ethpool. It provides the same level of mining efficiency and service as Ethpool, but pays out using the traditional and fair PPLNS mode. Payouts are instant and you will receive your Ether coins as soon as you reach a minimum balance of 1 ETH. The new pool supports Stratum mode using Stratum Proxy v0.0.5 by dwarfpool, Stratum mode using QtMiner and the more traditional Getwork mode using ethminer. The mining fee will is now reduced to 0% for the remaining week in order to make the new pool more attractive for users to switch to it, so you might want to give it a try.

– To check out the new Ethermine PPLNS Ethereum Mining Pool by Ethpool…

How to Fix Ethminer Not-Working Issues on 2GB GPUs

23, Mar 2016

ethminer-2gb-vram-error

It seems that owners of video cards with 2GB of video memory has started having issues mining Ethereum (ETH). People are reporting that their cards are not being able to properly allocate the DAG file needed for mining with Ethminer even though it is still well below 2GB in size (a little over 1.3 GB at the moment). The error people with 2GB VRAM GPUs trying to mine Ethereum are getting is the following:

Creating one big buffer for the DAG
Allocating/mapping single buffer failed with: clCreateBuffer(-61). GPU can’t allocate the DAG in a single chunk. Bailing.
clEnqueueWriteBuffer(-38)

There are numerous suggestions on how some people were able to resolve the problem and make their 2GB VRAM video cards able to mine again Ethereum without more problems, but it seems that now all of them work for everyone and in all cases. We have tried different suggestions and have experimented, until we have found out a working solution that works fine on an AMD Radeon R9 285 GPU with 2GB of video memory, so you might want to try and see if it will work for you as well. Try executing the following commands in Windows before running ethminer and see if it will help:

setx GPU_FORCE_64BIT_PTR 0
setx GPU_MAX_HEAP_SIZE 100
setx GPU_USE_SYNC_OBJECTS 1
setx GPU_MAX_ALLOC_PERCENT 100
setx GPU_SINGLE_ALLOC_PERCENT 100

Some people are reporting that they only need to do “setx GPU_MAX_ALLOC_PERCENT 100” and things work fine after that with their 2GB GPUs, but we were not able to make things work only with that variable. So do try and report what works and what does not for you, setting all of the four environment variable listed above did the trick for us. Restarting the computer after applying the environment variable listed above may be required for some users to make them work properly. Using 14.x drivers seems to provide the best success rate for most people, so if you are using newer 15.x drivers and still having issues, you might try going back to 14.x.

Linux users might try this as well, however you need to replace the setx with export and add = before the value you want to set, so the above list of commands needed for Linux users mining Ethereum should look like this:

export GPU_FORCE_64BIT_PTR=0
export GPU_MAX_HEAP_SIZE=100
export GPU_USE_SYNC_OBJECTS=1
export GPU_MAX_ALLOC_PERCENT=100
export GPU_SINGLE_ALLOC_PERCENT=100

Do note that we have not tested if this fixes the issue for Linux users, we can confirm that it worked for us under Windows, so if you test on Linux mining rigs with 2GB video memory GPUs please write in the comments if it helped you or not.


top