My testing: Cycles on an R9-390x + GTX 650 + i7 5820k on OpenCL

[John_Lancaster]

@eruanno

Thanks.
You shouldn’t expect something like that. The bandwidth/speed of Fury X’ HBM is 512 GiB/s, your Memory Bandwidth at 1720 MHz is ~440 GiB/s, so it’s not that huge of an improvement. However, the Fury will offer 56 Compute Units vs. 44 on the 2/390X (3.584 vs 2.816 Shader Processors). I don’t know how much improvement in rendering speed you will get, as the shader units seem to be a bit ‘underemployed’ while running cycles (power consumption is also low). So this is what I’m very curious for and hope, somebody with a Fury X might run the cycles benchmark scene. Also consider, the Fury has half the amount of Memory so you would be limited to less complex scenes.
The whine should come from coils/chokes not caps, btw. You get this while computing? If you talk from games, you could just use the new FRTC.

Ah.

Well the whine is no big deal unless I’m using SFM where it kinda annoys me. For some reason SFM makes it whine.

When I get the fury I will be running all sorts of blender tests.

[John_Lancaster]

@eruanno

Thanks.
You shouldn’t expect something like that. The bandwidth/speed of Fury X’ HBM is 512 GiB/s, your Memory Bandwidth at 1720 MHz is ~440 GiB/s, so it’s not that huge of an improvement. However, the Fury will offer 56 Compute Units vs. 44 on the 2/390X (3.584 vs 2.816 Shader Processors). I don’t know how much improvement in rendering speed you will get, as the shader units seem to be a bit ‘underemployed’ while running cycles (power consumption is also low). So this is what I’m very curious for and hope, somebody with a Fury X might run the cycles benchmark scene. Also consider, the Fury has half the amount of Memory so you would be limited to less complex scenes.
The whine should come from coils/chokes not caps, btw. You get this while computing? If you talk from games, you could just use the new FRTC.

Also HBM is 4096-bit.

[eruanno]

Would be great if you get a Fury and post results
Of course, the bus width is 4096, compared to the 512 bits of your 390X, 8x higher. But your GDDR5 I/O clock is 3.440 MHz, HBM is clocked at 500 MHz, so you can trust my numbers on the bandwidth, which is what really counts. Of course, HBM is a great technology but in terms of pure speed, the bus width is not the only factor.

BTW: your clocks are extraordinary high, I suppose Hynix GDDR5 chips? What Manufacturer is this card from?
btw2: you could also downclock your GDDR5 and directly see the impact of bandwidth on render time.

[eruanno]

Assumption confirmed: With 15.7 driver, I get 1:00, so about -20 seconds:yes: