On my side, I prefer use a dedicated app to benchmark instead of in game or benchmark in game. Because an app is developed to this purpose, optimized, with a low cpu consumption and also it's start faster than a game

Quoting: VinouchOn my side, I prefer use a dedicated app to benchmark instead of in game or benchmark in game.

hashcat does a fine bit of 'straight numbers' GPU benchmarking i would think.. And it doesn't even rely on having any GUI stuff running..

$ hashcat --benchmark
or
$ hashcat --benchmark > /tmp/example_gpu_benching.txt
to store the output for reviewing and to "diff" against when overclocking..

( example output: https://hastebin.com/osunebaxey )


With hashcat in combination with sensors , and a bit of grep, awk etc. , it'd probably be a relative breeze to script a speed vs temp. GPU benchmarking script thingy...



Last edited by Duck Hunt-Pr0 on 19 September 2020 at 7:35 pm UTC

Quoting: Duck Hunt-Pr0

Quoting: VinouchOn my side, I prefer use a dedicated app to benchmark instead of in game or benchmark in game.

hashcat does a fine bit of 'straight numbers' GPU benchmarking i think.. It doesn't even rely on any GUI running..

$ hashcat --benchmark
or
$ hashcat --benchmark > /tmp/example_gpu_benching.txt
to store the output for reviewing or to "diff" against when overclocking..

example output: https://hastebin.com/osunebaxey

These compute workloads aren't even remotely similar to how games or 3D graphics benchmarks make use of your GPU, so the results aren't very relevant. And the OP is specifically asking for a Vulkan benchmark.

Quoting: tuubiThese compute workloads aren't even remotely similar to how games or 3D graphics benchmarks make use of your GPU,

Oh..My bad .. I just happened to see the "[...]in order to adjust my overclocking" bit, and was thinking faster is better.. for 3D graphics in games as well as 'compute workloads'

Might i suggest checking rendering times (of an identical scene) using Blender? Or is that too perhaps something unrelated to 3D graphics performance?

Last edited by Duck Hunt-Pr0 on 19 September 2020 at 8:08 pm UTC

what about https://www.geekbench.com/
it has a VULKAN bench if you run
./geekbench5 --compute Vulkan

EDIT: i just saw it has an error on my AMD card for 1 test
ERROR:src/geekbench/workload/compute_workload.cpp(111)] workload 221 failed validation

but with ACO it works fine... so use
RADV_PERFTEST=aco ./geekbench5 --compute Vulkan

Last edited by mylka on 19 September 2020 at 9:08 pm UTC

Quoting: Vinouch..in order to adjust my overclocking.

Quoting: tuubiThese compute workloads aren't even remotely similar to how games or 3D graphics benchmarks make use of your GPU, so the results aren't very relevant. And the OP is specifically asking for a Vulkan benchmark.

I'm no expert in neither Vulkan nor GPU overclocking. So, could someone please explain to me how GPU overclocked performance might differ using Vulkan on a non-overclocked card, as opposed using Vulkan on an overclocked card?

- Are there some previously hidden Vulkan features that then suddenly become active?
- Does Vulkan perhaps suddenly do more levels of tessellation, if i overclocked my card?
- Does Vulkan perhaps suddenly do more sharper antialiasing, if i overclock?
- Does 2X texture scaling or filtering turn into 2.3X, with overclocking?
- Does Vulkan behave or react diffrerently from DirectX or OpenGL, with overclocking??
- Can i expect more than increased heat, powerconsumption, and computational speed from overclocking a GPU; Hopefully leading to faster frame rendering?

If the answer to either of those questions are 'No' , i'll refer back to my initial answer


Last edited by Duck Hunt-Pr0 on 20 September 2020 at 12:59 am UTC

Quoting: Duck Hunt-Pr0

Quoting: Vinouch..in order to adjust my overclocking.

Quoting: tuubiThese compute workloads aren't even remotely similar to how games or 3D graphics benchmarks make use of your GPU, so the results aren't very relevant. And the OP is specifically asking for a Vulkan benchmark.

I'm no expert in neither Vulkan nor GPU overclocking. So, could someone please explain to me how GPU overclocked performance might differ using Vulkan on a non-overclocked card, as opposed using Vulkan on an overclocked card?

- Are there some previously hidden Vulkan features that then suddenly become active?
- Does Vulkan perhaps suddenly do more levels of tessellation, if i overclocked my card?
- Does Vulkan perhaps suddenly do more sharper antialiasing, if i overclock?
- Does 2X texture scaling or filtering turn into 2.3X, with overclocking?
- Does Vulkan behave or react diffrerently from DirectX or OpenGL, with overclocking??
- Can i expect more than increased heat, powerconsumption, and computational speed from overclocking a GPU; Hopefully leading to faster frame rendering?

If the answer to either of those questions are 'No' , i'll refer back to my initial answer

No need to get snippy, friend.

My reply to you was not a personal attack. It was simply an observation that if overclocking makes your GPU 5% faster at a particular, focused compute benchmark, that might or might not correspond to a similar rise in game performance. Hell, it might mean that your games run 10% faster, or just 1%.

I think games or game-like benchmarks are the only realistic way to measure how much your overclocking actually helps games run better, if that is your goal. And even then you should test with several. Modern game/graphics engines are complex beasts, Vulkan or not, and their VRAM usage patterns, for example, are quite different from those of the benchmark you suggested.

And most importantly, this discussion is specifically about Vulkan benchmarks. Your suggestion was interesting, but maybe not that relevant. That was the entire point. No slight was intended.

To avoid misunderstand, I edited my first post.