The wait has finally come to an end: AMD Radeon RX Vega64 in test

Already at the end of last year we were able to marvel at the Vega64 in its first form and since then the manufacturer (and thus also the readers, as well as the potential customers) has fed us again and again with small bits of information and announcements about the n... Also at the risk of us repeating ourselves, we want to go back to the most important innovations at Vega. With the Vega64, AMD is now offering a new generation of GPUs after the Vega Frontier Edition, in which more than 200 changes are... Disassembly and radiator details Removing the top hee cover is easy. With a small Phillips screwdriver (PH1), the six small swivels that hold this cover can be turned out. After that, there is only one... Board layout The Vega64 and Vega Frontier Edition have the same board, 100% identical components and differ only by the soldered package with the halved memory expansion, as well as a customized firmware. The la... Foreword to gaming benchmarks On the following pages, we let the bars and curves speak for themselves and do without filling text. In return, and at the request of many readers, we have not only the overall overviews of all maps. Benchmarks in WQHD (2560 x 1440 Pixels) Benchmarks in Ultra HD (3840 x 2160 pixels) Benchmarks in WQHD (2560 x 1440 Pixels) Benchmarks in Ultra HD (3840 x 2160 pixels) Benchmarks in WQHD (2560 x 1440 Pixels) Benchmarks in Ultra HD (3840 x 2160 pixels) Benchmarks in WQHD (2560 x 1440 Pixels) Benchmarks in Ultra HD (3840 x 2160 pixels) Benchmarks in WQHD (2560 x 1440 Pixels) Benchmarks in Ultra HD (3840 x 2160 pixels) Benchmarks in WQHD (2560 x 1440 Pixels) Benchmarks in Ultra HD (3840 x 2160 pixels) Introduction Actually, we wanted to remove this game from the benchmark suite for good this time, because the quality of the DirectX12 implementation is not something you really want for yourself and the players. Nevertheless, the results were, so noticeable... Benchmarks in WQHD (2560 x 1440 Pixels) Benchmarks in Ultra HD (3840 x 2160 pixels) Benchmarks in WQHD (2560 x 1440 Pixels) Benchmarks in Ultra HD (3840 x 2160 pixels) Good question, short answer: Jain. The latest version of Claymore's Dual Ethereum AMD/Nvidia GPU Miner (v9.8) includes support for Radeon RX Vega, so we used it for our mining benchmark. All AMD cards run in the so-called... Preliminary remark on the three power modes In the Wattman, in addition to the standard setting (ex works), which is called Balanced Mode, you will also find the possibility to save energy with the Power Save Mode or, conversely, to use the Turbo Mode to... Temperature curve and clock rate The fan control is quite conservative, so that the maximum temperature of 85°C is reached relatively quickly. But then the card already has approx. 6% of their performance lost from the cold state, which is almost out of the... Better late than never and yes, we are really glad that this chapter of endless salami-slice-hold tactics is finally over. But you could have saved the whole media circus in advance, because with a slightly more relaxed...

Good question, short answer: Jain. The latest version of Claymore's Dual Ethereum AMD/Nvidia GPU Miner (v9.8) includes support for Radeon RX Vega, so we used it for our mining benchmark. All AMD cards run in so-called ASM mode, which requires final fine-tuning with the -dcri command-line option.

The tested Radeon R9 Fury X achieved its best hash rate with the default -dcri 85, while the Radeon R9 390X optimally shot at -dcri 20. After experimenting with fine tuning for the Sapphire Nitro+ RX 580 8GB, we ended up with even slightly higher hash rates using the -asm 2 switch for alternative ASM kernel mode.

With the Radeon RX Vega64, however, you couldn't do much wrong or better in the end. Deviating adjustments from the default -dcri 30 did nothing to influence performance again positively.

The most striking exception in our chart is the GeForce GTX 1080, which falls even further behind a GTX 1070. This is a known latency problem, because also the program code of our benchmark is optimized for GDDR5 and not for GDDRX5.

Both the 1080 Ti and Titan Xp elegantly bypass this bottleneck with their much wider 384-bit memory interface. If you could build your card from Nvidia's spare parts rack yourself, it would probably end up being a GP102 processor with a 384-bit bus with 9Gb/s GDDR5, which you can easily use on 10Gb/s. It would be nice, but unfortunately it doesn't work.

The good news for all gamers: AMD's Radeon RX Vega64 is apparently not (yet) the mining monster many might have hoped for. Well, at least not in the current state and with no further software optimized for Vega. However, if serious optimizations are still possible, this first statement is of course immediately relativized again.

We know that for professional mining, even the firmware is screwed around, that clock rates and latency are changed and thus in the end also much higher hash rates are possible than just so out-of-the-box. But neither AMD nor Nvidia wanted to comment on how high they see the hash performance themselves. And, of course, we must not forget that our values were created with reference cards in the factory state.

However, given the current price of Vega64, we suspect that miners will probably be more inclined towards a Radeon R9 390 or the RX 400/500 series and will continue to fish for maps in the bay. Even if this has already mutated into deep-sea fishing. The 500 euros for a black Vega64 seem more like a non-bargain. But who knows? Greed knows no bounds.

Pages: