Bitcoin Forum

Here is an interesting article about an "Efficient Bitcoin Miner System Implemented on Zynq SoC": http://www.xilinx.com/publications/archives/xcell/Xcell84.pdf

Interesting article.  Seems that they were able to get up to 3.8 Mh/s with a single core implemented.  I didn't see any mention of how much headroom they had left on the SOC to implement additional cores. Maybe its only one core per chip.  You need a lot more cores though to make it viable in today's world.  Wonder if Scrypt could be made to work on the ZedBoard?

It would never be 1 core per chip. That's about 15 years ago in processor design time.

Thanks for your history lesson, but I am referring to the "soft" mining core in the Programmable logic block of the Zynq-7000 discussed in the article.  Not hard-wired CPU cores. ;D

They referenced utilizing multiple mining cores connected to the embedded bitcoind node, but they did not expand on if they were able to create multiple soft cores on a single Zynq-7000. 

Just a curiosity.  As it would need about a 100 cores just to equal the hashing power of a USB block erupter. hahaha!

It is an interesting article but IMHO not a very good result! The high-level synthesis tool they used made their life easier, but their hasher is nowhere near as fast as it should be...

As for the Zedboard - it is cool, once you get over the learning curve of handling both the CPU/Linux and FPGA flow, but unfortunately the board seems to be lacking a bit in the PSU department - I managed 38MH/s on mine but while there was more room for hashers, adding anymore would brown it out!

The article only mentioned speed and such for spartan 3 and spartan 6, the main point with the article, the Zync, was not mentioned at all?, would be more interresting to see what they accomplished on that platform..