Bitcoin is an electronic currency that has become increasingly popular since its introduction in 2008. Transactions in the bitcoin system are stored in a public transaction ledger ('the blockchain'), which is stored in a decentralized, peer-to-peer network. Bitcoin provides decentralized currency issuance and transaction clearance. The security of the blockchain depends on a compute-intensive algorithm for bitcoin mining, which prevents double spending of bitcoins and tampering with confirmed transactions. This 'proof-of-work' algorithm is energy demanding. How much energy is actually consumed, is subject of debate. We argue that this energy consumption currently is in the range of 100-500 MW. We discuss the developments in bitcoin mining hardware. We also briefly outline alternative schemes that are less energy demanding. We finally look at other blockchain applications, and argue that also here energy consumption is not of primary concern.

We present a new VLIW core as a successor to the TriMedia TM1000. The processor is targeted for embedded use in media-processing devices like DTVs and set-top boxes. Intended as a core, its design must be supplemented with on-chip co-processors to obtain a cost-effective system. Good performance is obtained through a uniform 64-bit 5 issue-slot VLIW design, supporting subword parallelism with an extensive instruction set optimized with respect to media-processing. Multi-slot 'super-ops' allow powerful multi-argument and multi-result operations. As an example, an IDCT algorithm shows a very low instruction count in comparison with other processors. To achieve good performance, critical sections in the application program source code need to be rewritten with vector data types and function calls for media operations. Benchmarking with several media applications was used to tune the instruction set and study cache behavior. This resulted in a VLIW architecture with wide data paths and relatively simple cpu control.

No abstract