Posts by kasdashdfjsah
|
1)
Posted 20 Jan 2026 by kasdashdfjsah Post: I appreciate the technical breakdown regarding native FP64 support. You are correct that the M-series lacks dedicated hardware double-precision units, but framing this as an impossible barrier for 2026 is a bit of a legacy viewpoint. While PrimeGrid does leverage INT64, its success proves the stability and efficiency of the M-series iGPU for high-precision math. On my M4 Mac Mini, the iGPU handles these intense workloads with a fraction of the heat and noise of the CPU, finishing tasks 9x faster than the CPU cores for the same power draw. Regarding the "inefficiency" of FP64 emulation: even with a 4-12x penalty for emulating double precision via FP32, the parallel nature of the Apple GPU still offers a massive net gain over CPU crunching. Modern libraries like libMetalFloat64 have already demonstrated that "hardware double precision is not needed" to achieve competitive performance on Apple Silicon. By dismissing an Asteroids app based on 2018 hardware assumptions, we are ignoring the reality of 2026: Apple Silicon is the most efficient global compute resource we have. If projects like Einstein@Home and PrimeGrid have found the roadmap, it's time for Asteroids to stop looking for excuses and start looking at emulation or Metal-optimized alternatives. Science shouldn't wait for "perfect" hardware when we have "great" hardware sitting idle right now. |
|
2)
Posted 19 Jan 2026 by kasdashdfjsah Post: Asteroids@home has long been a favorite for GPU crunching, with solid support for NVIDIA and AMD via OpenCL and CUDA. However, there is a massive untapped resource being ignored: the Apple Silicon iGPU. For a long time, the excuse for not supporting the M-series GPU was a lack of native FP64 or the deprecation of OpenCL on macOS. But in 2026, those excuses are no longer valid. Projects like Einstein@Home and PrimeGrid have already proven that the Apple Silicon iGPU is more than capable of handling high-precision scientific math with incredible efficiency. On my base M4 Mac Mini, I am currently running 10 concurrent tasks on the iGPU for other projects with perfect stability. Apple Silicon’s unified memory architecture offers a unique advantage for memory-intensive projects like Asteroids, allowing the GPU to access huge amounts of data without the traditional PCIe bottleneck. By refusing to release an arm64-apple-darwin GPU application, Asteroids@home is leaving thousands of highly efficient M1, M2, M3, and M4 nodes on the table. We have the hardware, and other projects have already provided the roadmap. It is time to bring Asteroids@home into the modern era of Green Crunching on Apple Silicon. When can the community expect a test version for the Mac iGPU? |
|
3)
Posted 16 Jan 2026 by kasdashdfjsah Post: I’m planning a "Green Crunching" upgrade to replace my current Ryzen 3700/RTX 3060 desktop with a high-TDP (80W) Intel Panther Lake Mini PC once they ship in early February. I'm particularly interested in the Asteroids@Home performance on the new Xe3 iGPU (Arc B390). Given that this architecture finally re-introduces hardware-native FP64 (1:16 ratio) and is built on the 18A node, the science-per-watt should be a significant leap over previous Intel generations. I’ll be running a 64GB DDR5 setup to ensure the iGPU has plenty of shared memory for large work units. Has anyone else looked into the OpenCL 3.0 performance for this architecture yet? I’m happy to post logs and TPF (Time Per Frame) data once the unit arrives to help optimize the app for these new chips. |
|
4)
(Message 9343)
Posted 29 Dec 2025 by kasdashdfjsah Post: Suddenly I cannot add the project on my Apple Silicon Mac. Anybody who can help me out? |
|
5)
Posted 26 Dec 2025 by kasdashdfjsah Post: But both einstein@Home and primegrid support the apple silicon iGPU's, so clearly It's possible. |
|
6)
Posted 25 Dec 2025 by kasdashdfjsah Post: Hello Asteroids@home Team, I saw your fantastic progress with the new AVX-512 and ARMv8 applications this year. Given your clear commitment to supporting efficient new hardware, I am writing to request a native OpenCL 1.2+ application for the Qualcomm Adreno iGPU. The latest Windows on Snapdragon drivers have fixed many of the previous OpenCL shared memory bottlenecks. As more users adopt these efficient devices, having a native Asteroids app would be a major win for the community. I would be happy to help test any 'alpha' builds on my Snapdragon X hardware to help create more competition in the distributed computing space. |
|
7)
(Message 9165)
Posted 26 Sep 2025 by kasdashdfjsah Post: Are there no Nvidia GPU tasks available? Cause I am not getting any. |
|
8)
(Message 9088)
Posted 4 Aug 2025 by kasdashdfjsah Post: Not at 0 yesterday when I checked |
|
9)
(Message 9086)
Posted 3 Aug 2025 by kasdashdfjsah Post: Why I am not getting any work units on my OnePlus Pad 3 Android tablet? |
|
10)
(Message 9061)
Posted 19 Jul 2025 by kasdashdfjsah Post: Currently not getting any WU's on my Apple Silicon Mac, why? |
|
11)
(Message 8962)
Posted 25 Apr 2025 by kasdashdfjsah Post: Under "Computing - computer types", how come MacOS is not on the list, even though both both the M4 Pro and M4 chip is ranked pretty high on the "CPU models" list? |
|
12)
(Message 8958)
Posted 19 Apr 2025 by kasdashdfjsah Post: Ok, thanks for the response, hoping this will become possible one day :) |
|
13)
(Message 8956)
Posted 18 Apr 2025 by kasdashdfjsah Post: Would love to have work units available for the Adreno GPU in my Snapdragon chip, and not just CPU work units :) |
|
14)
(Message 8955)
Posted 17 Apr 2025 by kasdashdfjsah Post: Ok, thanks for the response. I'm using my CPU for another project, so I just have the GPU running Asteroids@Home currently. |
|
15)
(Message 8953)
Posted 16 Apr 2025 by kasdashdfjsah Post: How many WU's does 1 GPU task contain? Just asking cause for CPU tasks, each thread, in my case 16, gets it's own CPU task, but the GPU only gets 1 at a time. And also, the estimated completion time is just stuck at 11 minutes 45 seconds for my RTX 3060, and it took almost 5 minutes for the current GPU task to get to 0.01%, which is VERY big WU then, compared to the CPU tasks, which only take about an hour or so to complete on my 5700x CPU. So just curious about the differences between CPU and GPU tasks for this project :) Update: The GPU task just jumped, after about 9 minutes, up to 8% complete, then shortly after 16, 24, 32, and so on, jumping by 8% every 10 seconds, and then finished after a little over 10 minutes. |
|
16)
(Message 8908)
Posted 3 Apr 2025 by kasdashdfjsah Post: Tried to add the project, but the animation with the green dot going between the 2 computers went on for about a minute, before it said "failed to add project". |
|
17)
(Message 8882)
Posted 23 Mar 2025 by kasdashdfjsah Post: So I can see, but what is the end goal of this project? Will it just be up and running till the end of time? |
|
18)
(Message 8874)
Posted 22 Mar 2025 by kasdashdfjsah Post: How long will the current "Period Search Application" project run for, or just Asteroids@Home? Any estimate on when this project will finally run out of work units, or will the area or number of asteroid mapping or whatever just keep expanding? |
|
19)
(Message 8817)
Posted 21 Feb 2025 by kasdashdfjsah Post: Available to… think you missed a few worss there at the end :) |
|
20)
(Message 8813)
Posted 21 Feb 2025 by kasdashdfjsah Post: Server status page says 0 work units available to send since yesterday, why? |
Next 20