Message boards :
Number crunching :
Why are the benchmark results under Ubuntu/linux are nearby doubled ?
Message board moderation
Author | Message |
---|---|
The_Matrix Send message Joined: 17 Nov 03 Posts: 414 Credit: 5,827,850 RAC: 0 |
Hey, i am running this host on Beta: https://setiweb.ssl.berkeley.edu/beta/show_host_detail.php?hostid=82307 Now watch this under Windows 10...unbelievable... https://setiweb.ssl.berkeley.edu/beta/show_host_detail.php?hostid=81991 Never noticed this before, I'll never crunch under windows again... Greetings. Can be closed must have been a database error, i am clueless !? |
Stephen "Heretic" Send message Joined: 20 Sep 12 Posts: 5557 Credit: 192,787,363 RAC: 628 |
Hey, i am running this host on Beta: . . Not at all sure what you are saying but if you are running CUDA80 then yes it is very fast. I would love to see a version come out for Windows but I am not optimistic at this point Stephen . |
The_Matrix Send message Joined: 17 Nov 03 Posts: 414 Credit: 5,827,850 RAC: 0 |
Not right now, at the moment i am running only cuda 6.0 , hope there will be a 8.0 to crunch. |
Mr. Kevvy Send message Joined: 15 May 99 Posts: 3776 Credit: 1,114,826,392 RAC: 3,319 |
Not right now, at the moment i am running only cuda 6.0 , hope there will be a 8.0 to crunch. The work units are not marked by the project for CUDA version or even whether to run on CPU or GPU; your local BOINC client does that. It's only checked that the correct host is returning them and not the platform they were computed on. |
rob smith Send message Joined: 7 Mar 03 Posts: 22190 Credit: 416,307,556 RAC: 380 |
It is not CUDA8 that is very fast, but the application that Petri & Tbar have very heavily optimised that is very fast - indeed the application it is pretty fast when running with CUDA6 libraries. Bob Smith Member of Seti PIPPS (Pluto is a Planet Protest Society) Somewhere in the (un)known Universe? |
HAL9000 Send message Joined: 11 Sep 99 Posts: 6534 Credit: 196,805,888 RAC: 57 |
Hey, i am running this host on Beta: I guess you are referring to the benchmarks? Which are mostly meaningless. The benchmark values can vary greatly just between versions of BOINC. SETI@home classic workunits: 93,865 CPU time: 863,447 hours Join the [url=http://tinyurl.com/8y46zvu]BP6/VP6 User Group[ |
The_Matrix Send message Joined: 17 Nov 03 Posts: 414 Credit: 5,827,850 RAC: 0 |
I guess you are referring to the benchmarks? Which are mostly meaningless. Thx, that's good to know. Unfortunately i noticed a 5 watts lower usage on my power supply when i using linux. I'll run on linux in future. |
Keith Myers Send message Joined: 29 Apr 01 Posts: 13164 Credit: 1,160,866,277 RAC: 1,873 |
The BOINC profiling benchmarks are solely CPU based. I've never heard of a reason why the very same processor benchmarks 50% faster on a Linux system compared to a Windows system. I've only concluded that the Linux system is more efficient in running CPU benchmarks compared to a Windows system simply because of less background tasks or simply better core processing improvement. Seti@Home classic workunits:20,676 CPU time:74,226 hours A proud member of the OFA (Old Farts Association) |
The_Matrix Send message Joined: 17 Nov 03 Posts: 414 Credit: 5,827,850 RAC: 0 |
Must be a small fault of my system, and its almost over 5 years "old". Somethings going ugly at this system, hopefully my mainboard won't fault. That will be expensive to replace (socket 1155). |
Grant (SSSF) Send message Joined: 19 Aug 99 Posts: 13731 Credit: 208,696,464 RAC: 304 |
I've only concluded that the Linux system is more efficient in running CPU benchmarks compared to a Windows system simply because of less background tasks or simply better core processing improvement. Or the benchmark code is different. Different OS, different compilers, different switches, different results. Or has always occurred- optimisations to give good results in certain benchmarks. eg Google have recently announced the retirement of their Octane benchmark. It was meant to test the JavaScript performance of a system/device, however over time VM developers have been optimizing their software to improve it's Octane performance, unfortunately that boost hasn't been reflected in real world performance. Hence the retirement of the benchmark. Grant Darwin NT |
Grant (SSSF) Send message Joined: 19 Aug 99 Posts: 13731 Credit: 208,696,464 RAC: 304 |
Unfortunately i noticed a 5 watts lower usage on my power supply when i using Generally; the lower the power usage when under a given load, the less work being done, and the longer it takes, and so more power is used overall. Grant Darwin NT |
jason_gee Send message Joined: 24 Nov 06 Posts: 7489 Credit: 91,093,184 RAC: 0 |
The BOINC profiling benchmarks are solely CPU based. I've never heard of a reason why the very same processor benchmarks 50% faster on a Linux system compared to a Windows system. I've only concluded that the Linux system is more efficient in running CPU benchmarks compared to a Windows system simply because of less background tasks or simply better core processing improvement. For technical background, it helped having looked at the source code for the bench, along with the history of Whetstone, in context of the hardware and OS changes since the Boinc client was originally devised. -Whetstone originally was FPU-Serial only - It was designed and improved to defeat common compiler 'tricks' that remove code or avoid loops - SIMD floating-point became common with Pentium-3, with SSE, and required hand vectorisation to use - Some dedicated SIMD versions of Whetstone were developed, though were not put in Boinc client Code. - 64 Bit Windows requires At least SSE2 on Windows, so the compiler is geared to use that *. ---> (*This caused quite some grief trying to make 64 bit Windows applications in the past, since a lot of code used to be 80-bit FPU based) - Compilers (especially GCC on Linux) became better at vectorising automatically, only relatively recently, either optional or by default, depending on compiler options. -------------------- - The Boinc client code suggests the naive approach was used, specifically leaving optimisation to the compiler, meaning the bench will compile differently on every compiler+platform combination [Bad Idea for any bench code] - For 'True' Whetstone, it should have either enforced serial scalar implementation even on SIMD, or, -Alternatively had a way to differentiate SIMD vector length on client + apps, on the server, or, - a bench per functional vector length. The different vector length performance of Whetstone, 'proper' serial Vs SIMD of various vector lengths, is what drives the discrepancy . You can view this by running Sisoft Sandra Lite single threaded Whetstone benchmarks, at each of the vector lengths. This is one of the main 3 or 4 driving design flaws with estimates that break CreditNew, especially displaying noticeable irregularities when efficient SIMD implementations were added to stock CPU application code, then again more recently when AVX was added. "Living by the wisdom of computer science doesn't sound so bad after all. And unlike most advice, it's backed up by proofs." -- Algorithms to live by: The computer science of human decisions. |
Keith Myers Send message Joined: 29 Apr 01 Posts: 13164 Credit: 1,160,866,277 RAC: 1,873 |
Thank you very much, Jason for explaining the differences in benchmark profiling between modern Linux and Windows systems. It makes sense. Also why the apt derogatory of "Credit_Screw" is so richly deserved. :-} Seti@Home classic workunits:20,676 CPU time:74,226 hours A proud member of the OFA (Old Farts Association) |
jason_gee Send message Joined: 24 Nov 06 Posts: 7489 Credit: 91,093,184 RAC: 0 |
Thank you very much, Jason for explaining the differences in benchmark profiling between modern Linux and Windows systems. It makes sense. Also why the apt derogatory of "Credit_Screw" is so richly deserved. :-} Lol, since stumbling across that little chestnut (which amounts to abuse of Whetstone) generating factor of 2-8 times meaningless numbers for estimates, I'll get my little dig in at every opportunity. Can't wait for AVX512, where I will pull out the beer and popcorn :D "Living by the wisdom of computer science doesn't sound so bad after all. And unlike most advice, it's backed up by proofs." -- Algorithms to live by: The computer science of human decisions. |
©2024 University of California
SETI@home and Astropulse are funded by grants from the National Science Foundation, NASA, and donations from SETI@home volunteers. AstroPulse is funded in part by the NSF through grant AST-0307956.