AMD Radeon VII Achieves ~100MH/s Mining ETH

AMD has taken the performance crown for Ethereum mining once again with the Radeon VII. The Radeon VII manages to overtake Polaris, Fiji, the Titan V, and Turing all at once, but will it make mining profitable again?

Out of the box in stock configuration, the Radeon VII manages to pull off a whopping 90MH/s, nearly triple the performance of a stock RX Vega 64, is 29% faster than the Radeon Pro Duo, and beats the Titan V by a large margin. The RX Vega 64 is quite a bit behind the Radeon Pro Duo, and the Pro Duo trails slightly behind the Titan V in terms of the raw hash rate at stock configurations.

Related AMD’s Navi GPUs Confirmed to Retain GCN Design

GPU Stock MH/s Optimized MH/s
Radeon VII 90 ~100
Titan V 69 82
Radeon Pro Duo (Fiji) 64
RX Vega 64 32 44

After tweaking the Radeon VII, it is possible to achieve a hash rate between 90MH/s and 100MH/s. According to VoskCoin over at BitcoinTalk, the following configuration brings in 91MH/s at 251 watts. This configuration provides an efficiency improvement of 21% over the stock 319-watt power consumption.

Configuration Core Voltage Core Clock Memory Clock Power Limit Power Consumption
Stock 1136mV 1801MHz 1000MHz +0% 319W
Optimized 950mV 1750MHz 1100MHz +0% 251W

Compared to the Titan V, the Radeon VII is a much more compelling option.  The Radeon VII is immensely cheaper, now available for $680 – $700, whereas the Titan V is within the $3000 range, and the Radeon VII achieves a higher hash rate per watt. Compared to Polaris, Radeon VII is a more efficient option. The Radeon VII draws less power than three RX 570s/580s and will occupy a single PCIe slot rather than three, enabling higher performance density in mining rigs, and less heat output. As for the Radeon Pro Duo, for miners interested in mining multiple coins, the dual-GPU design may be desirable. With a dual-GPU, miners have the ability to dedicate one GPU too, say, ETH, and the other to XMR, making it a dynamic card.

The Radeon VII’s increased hash rate is largely due to the massive improvement of memory bandwidth over Vega 10. The RX Vega 64 has a memory bandwidth of 484GB/s and 8GB of HBM2, whereas the Radeon VII boasts a memory bandwidth of 1TB/s and 16GB of HBM2. The RX Vega 64 has a TDP of 295W, compared to the Radeon VII’s 300W TDP, making the Radeon VII a much more efficient card at the same power consumption. The Radeon VII also has a higher maximum temperature.

The Radeon VII typically trades blows with the NVIDIA GeForce RTX 2080, but in some cases, such as in World War Z, the Radeon VII, let alone the RX Vega 64, manages to beat the RTX 2080 Ti. TweakTown had also reported the Radeon VII surpassing the RX 2080 Ti, and the RX Vega 64 surpassing the GTX 1080 Ti in the Division 2 at 1080p and 1440p.

Leave a Comment

Your email address will not be published. Required fields are marked *

Scroll to Top