p.3 #3 · June 2026 LRC/PS updates ... faster Denoise measurements for Mac M with Neural Engine
Not really related to Denoise, but Mac prices just took a jump. I feel a little smug as I bit the bullet and ordered a pretty high end M5 Max MBP last week. Cost just increased by ~$1500 ...
p.3 #7 · June 2026 LRC/PS updates ... faster Denoise measurements for Mac M with Neural Engine
mcbroomf wrote:
Not really related to Denoise, but Mac prices just took a jump. I feel a little smug as I bit the bullet and ordered a pretty high end M5 Max MBP last week. Cost just increased by ~$1500 ...
I'm currently exploring options at reducing my storage footprint, primarily by addressing how I retain outtakes. I'm also debating rolling back to 12MP image capture options.
p.3 #8 · June 2026 LRC/PS updates ... faster Denoise measurements for Mac M with Neural Engine
Interesting article based on a Gurman/Bloomberg rumor that Apple will skip the M6 Pro and Max chips and go from M5 versions to M7 to get more on chip AI performance. It impacts this type of processing as the Pro and Max variants are how we access high GPU cores which drive this. A nugget at the end saying an M5 Ultra Studio is still on the cards with 80 GPU cores.
p.3 #10 · June 2026 LRC/PS updates ... faster Denoise measurements for Mac M with Neural Engine
mcbroomf wrote:
Interesting article based on a Gurman/Bloomberg rumor that Apple will skip the M6 Pro and Max chips and go from M5 versions to M7 to get more on chip AI performance. It impacts this type of processing as the Pro and Max variants are how we access high GPU cores which drive this. A nugget at the end saying an M5 Ultra Studio is still on the cards with 80 GPU cores.
p.3 #11 · June 2026 LRC/PS updates ... faster Denoise measurements for Mac M with Neural Engine
Here’s the updated table and a couple of graphs. (I will redirect the links to post #9 and just update this page from now on).
In the past the denoise time has correlated well with # of GPU cores. I had used data provided by Artisright some time ago and I may do that again if he updates it. There seemed no point in plotting vs Neural Engine cores as, except for Ultra chips, the core count is the same. So I stuck with GPU and got a reasonably good correlation (1st graph below), so it appears that the NE is accelerating the GPU and more (GPU) is better, no shock. It makes sense that there are more NE cores for the Ultra, to ensure full acceleration. I guess that 16 is enough for all other configs and simplifies chip design.
While the correlation is OK I wanted to take into account that each generation, M1-> M2 etc gets faster, either by design or by process shrink (which speeds up transistors). I could have tried scouring the web to get speed tests for each device, GPU or CPU as a stand-in, but I took the easy way out and just used a 10% multiplier for each new rev. So M2 runs 10% faster than M1 (x 1.10), M3 would run 21% faster than M1 (1.10 x 1.10) etc. Rather than divide these values into the denoise time I multiplied them by the GPU core count and came up with what I called Virtual Cores on the horizontal axis (2nd graph). As you can see it tightens up the correlation a little though there are a couple of outliers.
So how useful is this? Not very .. just playing with numbers here. The table might be of some use if you plan to upgrade and AI/Denoise is important to your PP workflow/time. Set your pain threshold for Denoise time then look at configurations (GPU core count especially) that have better results. Discard older revs if you don’t want to buy used.
PS. I used M5 as the chip rev (and multiplier) for the device in the Neo. I read that is it on the 3nm process at TSMC.
p.3 #15 · June 2026 LRC/PS updates ... faster Denoise measurements for Mac M with Neural Engine
hoodlum90 wrote:
It would interesting to see a couple of newer Windows systems with non-integrated GPU for comparison.
If anyone has a system and would like to run the test on the reference file then please post the times and system specs (CPU/GPU/RAM and I'll add it to the table. Even a system that might not be new but has a recent(ish) GPU upgrade.
p.3 #17 · June 2026 LRC/PS updates ... faster Denoise measurements for Mac M with Neural Engine
Matt suggested I re-order the table; M rev, then chip type, the GPU core. I added a 2nd table below the graphs (I still like to be able to see the table in denoise time order). Ignore the colour of the chip type, I used it to order that column so that it came out Base < Pro < Max < Ultra
