ReBench - benchmarking Renoise and your CPU.

  1. “desktop” / 100% power profile like toblerpone suggested

Forgive my ignorance, was just about to try another bench but I am not entirely sure how to go about “100% power profile.”

Abissus: I don’t remember exactly (OSX now), but in energy settings.

just push start and type “power options”

also turn off your antivirus and everything that might take up cpu processing, you might be able squeeze a bit more by enabling a high contrast theme (disables any aero features as you can’t otherwise in 8.1 (maybe you can in 10, I don’t know yet) it’s also not very clear if it was a retirement, but disabling fpattern follow and opening a non-pattern tab with any meters or scopes not vissible should increase your result by around 20%)

aero disabling? really?? Is this still 1995 ?

ffx: it ads a small %
or do you think that’s cheating? :stuck_out_tongue:

its dos then again. And yes, renoise was made for win not for dos. Its cheating.

just push start and type “power options”

also turn off your antivirus and everything that might take up cpu processing, you might be able squeeze a bit more by enabling a high contrast theme (disables any aero features as you can’t otherwise in 8.1 (maybe you can in 10, I don’t know yet) it’s also not very clear if it was a retirement, but disabling fpattern follow and opening a non-pattern tab with any meters or scopes not vissible should increase your result by around 20%)

Aah I understand. Something i did when I first got the PC, so no problems there.

I will disable anti virus and the options you suggested.

I can disable Aero via software called “Ultimate Windows Tweaker” (I have begun using it after my last bench), though it seems as this may be “cheating?”

At the moment I have only used it for a few minor things that I doubt will really affect performance, though I am happy to list if necessary. Also If the purpose is to lessen cpu processing, I can use UWT to increase performance further too.

no, we were joking about “cheating”… I only mentioned because then, windows looks like it was 1995. And I doubt that aero will have such huge impact on performance, although it’s pure crapware.

I remember another leet windows nerdz haxx: Set priority to background services (somewhere)… I also remember when I had an and k6, it helped :stuck_out_tongue:

You can also install hackintosh of course, if you want to have a REAL computer…

“Set priority to background services (somewhere).”

System:Performance:Advanced

But it will only make things worse.

You can also install hackintosh of course, if you want to have a REAL computer…

haha, not likely :stuck_out_tongue: teehee.

no, we were joking about “cheating”… I only mentioned because then, windows looks like it was 1995. And I doubt that aero will have such huge impact on performance, although it’s pure crapware.

Aah ok, completely missed that one. :smashed:

Yeah, I haven’t really bothered tweaking too much as I haven’t felt the need so far.

Have a few things I want to do today, after that I will have another you beaut red hot go at it…

Thanks for doing this thread!

am looking to upgrade, probably to Haswell i7 soon; I understand it keeps my options more open than Skylake for Windows 7 installs.

Here are my current results for stock Q6600, Win 7 (no AV disabling, just how I run renoise normally):


Intel Q6600 core2 Quad 2.4Ghz (stock) - 1CPU,latency 10ms : 11 RPTS

Intel Q6600 core2 Quad 2.4Ghz (stock) - 4CPU,latency 10ms : 24 RPTS

Intel Q6600 core2 Quad 2.4Ghz (stock) - 1CPU,latency 100ms : 21 RPTS

Intel Q6600 core2 Quad 2.4Ghz (stock) - 4CPU,latency 100ms : 51 RPTS

So, my 4 cores @100ms looks the same ballpark as a Haswell i7 on 1 core at the same, nice too see!

Hm a core2quad isnt THAT bad… Did you check the power profile?

Ledger: those results don’t seem right at all. Worse case scenario you should be getting around 40-50 for 4CPU

Not too sure really,

power profile set to high performance. When I upgraded from E6300 core duo I was getting about 3X performance which seemed to agree with Passmark results so I`ve never really questioned it. Maybe cheap Foxconn motherboard?

New Computer Test Yay!

Haswell Xeon 1231 v3 3.4GHz-- similar to i7 without onboard graphics

Interestingly got significant improvements on multi CPU, when I slotted my RAM properly in non-consecutive slots for dual channel operation (16GB; 2X8 Kingston HyperX 1600MHz):

1) RAM in Single Channel operation

1 core 10ms = 45
8 cores 10ms = 116

1 core 100ms = 57

8 cores 100ms = 159

2) Dual Channel operation

1 core 10ms = 45

8 cores 10ms = 121 (+6 RPTS)

1 core 100ms = 58 (+1 RPTS)

8 cores 100ms = 174 (+15 RPTS)

3) RAM Dual Channel and Windows 7 64bit set to high performance power mode

1 core 10ms = 45

8 cores 10ms = 120

1 core 100ms = 58

8 cores 100ms = 199

Minimising renoise GUI seemed to give higher results but not really real world so didn`t bother with full test.

Thanks toblerpone and ffx for the power mode tip! Got me an extra 25 RPTS @ 100ms!

Could you disable your antivirus and open the phrase tab with the spectrum analyzer disabled (in high performance)?

Thanks.

because I’m thinking of upgrading as well

Ok here it is:

Xeon 1231 v3

  • Mobo: Asus B85M-G PLUS/USB 3.1 (micro ATX)

  • RAM: 16GB 2x8GB in Dual Channel config Kingston 1600MHz

  • Win 7 64bit

  • Direct Sound

  • AV = off

  • Power mode = high performance

  • Phrase Editor focused with no phrase playing

  • Renoise master Vu meter is active (horizontal one at the top of the screen)

  • No spectrums or osciliscopes

The (+X) is improvement from my previous best results above

90% renoise CPU cut out RPT values:


1 core 10ms = 48 (+3)
8 cores 10ms = 127 (+7)

1 core 100ms = 59 (+1)
8 cores 100ms = 202 (+3)


So some improvements but not as major it seems as the dual-channel/high performance mode bumps (though these have not been tested independantly)

Also to note it is a fairly fresh Windows install and only critical updates have been installed. Whether or not non critical updates would improve/ hinder I don`t know.

Think Im edged out by the i7s, maybe we could do with a graph for all the individual best results in this thread! :slight_smile:

Also worth noting for Haswell refresh upgrades, some mobos (at least Asus) dont support the Haswell Refresh chips until a certain BIOS update. Fortunatly the Asus B85M-G PLUS/USB 3.1 seems to be a late enough board revision, that it worked out of the box. With the current/ last gen Asus boards you seem to be able to update the bios without posting the CPU via a specified USB port. However its another hoop to be aware of that I`d rather avoid.

If unsure and you want to go Haswell the non-refresh chips should be safer with this issue though slightly less performance.

If going Skylake you do get more common choices of M.2 onboard slotted ssds. More possible RAM capacity and DDR4. More choice for USB 3.1 boards too.

The reason I went with Haswell was no potential problems trying to load up Win 7 via USB ports and a bit lower cost overall which the graphics-less Xeon helped with too.

Ok Further Developments, by unpluging my USB 2 Audio interface (Spl Crimson) I was able to get another 14 RPTS on 100ms. So even on direct sound it looks like audio interface/ card is going to make some difference. This might explain my poor Q6600 results aswell:

So my max score with a completely silent renoise where I can`t see the pattern editor aswell!

is :

8 cores 100ms = 216

Well, IMHO firewire is quite a “good” invest currently, since prices for used firewire audio interfaces are massively dropping, thanks to Apple, not supporting it anymore (only officially, yes there is still a firewire driver in OSX 10.11) and trying to force to people to use useless thunderbolt + 20 adapters.

A PCIe 1x firewire card with TI chipset is about 10 €. So for around 150-200, you will get an audio interface which did cost over 1000 € some years ago. Of course have a look first, if there is still a driver for recent Win/OSX.