AMD Threadripper 1950x @ 3.8Ghz
ReBench.xrns - Passed all patterns with max load 37%
ReBench_256.xrns - Passed all patterns with max load 56%.
Rebenchmarked my system with Renoise 3.4 using the rebench_x256.xrns.
i7 4770, macos 10.14.6 at 44.1khz, 8ms, 4 core (8 virtual), 4k->4.5k resolution upscaling(heavy cpu load), 90% overload protection setting:
Renoise 3.4: 248 RPTS (it started to crackle around 190)
Renoise 3.3: 153 RPTS (crackling started around 140)
Renoise 3.1 with 1080p monitor, 10ms, osx 10.9.4: 207 RPTS
M1 Max (MBP 14) - passed (max cpu usage ~61%) all patterns from ReBench_x256 using built-in audio, 2ms latency and with dithering on, on Renoise 3.4 ARM with Metal rendering.
1 Like
Macbook 2020 M1 “normal” lol
renoise 3.4
dither off 90% warning
rane 72 soundcard
rebench 256
some limited amount of backround processes, about 10% maybe 20% of one cpu, normal usage situation
latency 01 8 cpu core = 217
latency 10 8 cpu core = PASS ALL 256 max 70%
latency 10 1 cpu core= 95
And real live comparision vs 2012 mid macbook. Orchestral project that i needed to render parts and use renders, freeze etc, in native mode with only few bridged plugins is around 40%cpu and a lot lower latency.
1 Like
Rebench 256
Intel(R) Xeon(R) CPU E3-1270 v5 @ 3.60GHz (win10 pro with 64 GB ram) - bought 2017… Dell…
Renoise 3.3
Latency. 10ms
1cpu - trk 41
8cpu - trk 144
Latency: 100ms
1cpu - trk 67
8cpu - trk ALL (began playing from 1 again)
Renoise 3.4
Latency: 10ms
1cpu - trk 36
8cpu - trk 180
Latency: 100ms
1cpu - trk 68
8cpu - trk 249
Since the 3.3 test was made after i did the 3.4 test i re-ran the 3.4 test in which it passed with 8 cpu and 100ms… Which has lead me to belive it might have been an unlycky coincidence where the scan of midi-devices occured at about track 249 the last time…
Interesting would be: benchmark in 3.3 and then 3.4.
re-ran mine…
1 Like
AMD Ryzen 9 3900X 12-Core Processor, 3800 Mhz, Win 10 Pro, 64 GB RAM, 44100 kHz, Focusrite ASIO.
Multicore:
Latency: 1.5 ms
All pass: 55% CPU.
Latency: 5,8 ms
All pass: 41% CPU.
Single core:
Latency: 5.8 ms
85 RPTS
3.3.2 and 3.4 perform exactly the same.
Intel i5-9600k, 3.7GHz, 6 Cores, Win 10 Pro, 16 GB RAM, Renoise 3.4
1 CPU: 63
6 CPU: 227
My CPU is almost perfect for my music but I could use one or two more cores to be fully comfortable
1 Like
ReBench_256.xrns
CPU: _____________ Intel i9-12900K | 8x P-Core 4.9-5.2Ghz + 8x E-Core 4.0Ghz | 24 Threads
OS: ______________ Win 11
Interface: _______ ASIO
Latency: _________ 5 ms
Renoise 3.3, 01 CPU: 161 RPTS
Renoise 3.3, 02 CPU: All Pass w/ 82.2% peak CPU Load
Renoise 3.3, 24 CPU: All Pass w/ 26.0% peak CPU Load
Renoise 3.4: same as 3.3
CPU: _____________ Intel i7-5820K | 6x 4.3Ghz | 12 Threads
OS: ______________ Win 11
Interface: _______ ASIO
Latency: _________ 5 ms
Renoise 3.4, 01 CPU: 68 RPTS
Renoise 3.4, 02 CPU: 128 RPTS
Renoise 3.4, 12 CPU: All Pass w/ 74.0% peak CPU Load
CPU: _____________ AMD Ryzen 3600 | 6x 3.9-4.2Ghz | 12 Threads
OS: ______________ Win 10
Interface: _______ ASIO
Latency: _________ 5 ms
Renoise 3.4, 01 CPU: 78 RPTS
Renoise 3.4, 02 CPU: 140 RPTS
Renoise 3.4, 12 CPU: All Pass w/ 75.0% peak CPU Load
CPU: _____________ Intel i5-4670K | 4x 3.6-3.8 Ghz | 4 Threads
OS: ______________ Win 10
Interface: _______ ASIO
Latency: _________ 5 ms
Renoise 3.4, 01 CPU: 52 RPTS
Renoise 3.4, 02 CPU: 78 RPTS
Renoise 3.4, 04 CPU: 163 RPTS
2 Likes
Renoise 3.4.1 (multicore = on / pdc = on)
142
Audio UMC Asio running at 48 kHz.
Buffersize: 128 samples (~2,7 ms).
OS: Win 10 Pro 21H2 / .1620
Board: MS-7B48 (MSI Z370-A Pro)
BIOS-Version/-Datum American Megatrends Inc. 2.C0, 04.06.2020
SMBIOS-Version 2.8
Processor: Intel(R) Core™ i7-9700K CPU @ 3.60GHz, 3600 MHz, 8 Kern(e), 8 logische(r) Prozessor(en)
RAM: Installierter physischer Speicher (RAM) 48,0 GB (DDR4) 1,2 gHz Dram / Uncore ~4,3 gHz
Pagefile: Größe der Auslagerungsdatei 14,0 GB
Gfx: Intel UHD 630 / Nvidia RTX2080 (8 GB)
The test stopped at 68 % due to activated overload prevention in the preferences.
Wow, that’s pretty impressive. Especially the single core performance.
ReBench 256 tracks and 1527 effects at the end!
- Software: Windows 11 Pro - Renoise 3.4.1
- Hardware: CPU: Intel i7 6700K, RAM: 32 GB DDR4, Sound Card: Sound Blaster ZxR PCIe
- Audio CPUs (latency 10 ms): 1 → 61 RPTS (trk: 60, fx: 360).
- Audio CPUs (latency 15 ms): 1 → 65 RPTS (trk: 64, fx: 384).
- Audio CPUs (latency 20 ms): 1 → 65 RPTS (trk: 64, fx: 384).
- Audio CPUs (latency 10 ms): 4 → 173 RPTS of 257.
- Audio CPUs (latency 15 ms): 4 → 188 RPTS of 257.
- Audio CPUs (latency 20 ms): 4 → 185 RPTS of 257.
- Audio CPUs (latency 10 ms): 8 → 247 RPTS of 257. Near!
- Audio CPUs (latency 15 ms): 8 → ~CPU: 83.0%: Ta! Amiga Rulez!!!.
The sound of this song reminds me of an old paper press machine for printing 
1 Like
that’s exactly why i wanted to get one in the first place.
this CPU is totally bonkers in terms of single-threaded performance, especially since you can easily let it boost to 5.5-5.7Ghz for single core usage and take back the clock and voltage for heavy load (4+ threads).
perfect for renoise and realtime audio in general.
I was interested to compare these to the M1 Pro:
Rebench 256, M1Pro, macos 10.16.1, Renoise 3.4.1, 5 ms, 44.1kHz:
1 core: 97 RPTS
2 cores: 177 RTPS
3 cores: 256 RTPS
10: cores: all passed with peak of 55%
Indeed that Intel CPU has an impressive single core performance. But keep in mind that M1Pro is a mobile cpu, and the fan did not even seem to have kicked in. Maybe this is a sign that Renoise still could use the M1Pro even more efficiently. This performance is more than enough for me. I understand though that Apple is not attractive for a lot of people and always comes with annoying compromises. I wonder how your CPU would perform under macos/hackintosh, since after reading the numbers here, it seems to me that the macos Renoise actually can perform a bit better than the Windows version…?
1 Like
Single core result would be interesting, too! Maybe with 5ms / 44.1kHz, just like above, so we could more accurately compare here.
The M1 ARM CPUs are indeed way more power efficient relative to the performance you can get out of the latest x86 offerings from Intel. I’m pretty sure that x86 will get in serious trouble throughout the next years, when Apple refines their CPUs and the architecture gets more widely natively supported by software.
i’m not sure how well hackintosh would perform with Intels Alder Lake platform, which utilizes Performance and Efficiency cores, since the OS’s thread scheduler needs to spread the loads correctly across those cores, in order to avoid workloads from running with pulled handbrake on E-Cores, when P-Cores would’ve been more adequate. I would have not migrated to Win11 if Win10 could have done that properly in all cases.
edit
a quick google revealed, that macOS will not differentiate between P- and E-Cores:
“XNU scheduler does not distinguish core types in macOS and will work no better than current Windows 10 in terms of core assignment.”
source: Intel Z690 compatibility with macOS | Dortania
macOS Installation on this platform does not seem like a walk in the park ;-(
1 Like
Sure, updated my benchmark. Can only use 4,4 or 5,8 ms latency with ASIO, though.
1 Like
Well investigated, directly from the main opencore dev 
Indeed this does not look like a good option currently, but I am quite sure they will have patched everything within a year.
@Drop_Shadow Thanks.
1 Like
Windows 7 x64 SP2+ ESU
Ryzen 5950X 3.4@4Ghz/64Gb RAM 3600@3800/NVMe 980 Pro
ESI Maya 44 eX PCIe
Renoise 3.4.1 Reg
ASIO/48Khz/~5ms
CPU overload protection: 98%
1CPU reached:
track:77
fx: 456
Cracks appeared at track 76
2CPU reached:
track:171
fx: >1000
Cracks appeared at track 138
32CPU reached:
track:257 and without any problems reached [Ta! Amiga Rulez!!!]
fx: >~1500
No cracks at all
Max Load: 24%
1 Like