- 2017.11.20 17:34 "Re: [Tiff] TIFF tag and compression registration", by Bob Friesenhahn
-
2018.01.16 20:08 "Re: [Tiff] Strategies for multi-core speedups", by
-
2018.01.16 00:15 "Re: [Tiff] Strategies for multi-core speedups", by Bob Friesenhahn
-
2018.01.15 21:41 "Re: [Tiff] Strategies for multi-core speedups", by Larry Gritz
- 2018.01.15 19:17 "[Tiff] Strategies for multi-core speedups", by Larry Gritz
- 2018.01.15 21:46 "Re: [Tiff] Strategies for multi-core speedups", by scott ribe
-
2018.01.16 01:09 "Re: [Tiff] Strategies for multi-core speedups", by Craig Bruce
-
2018.01.16 18:36 "Re: [Tiff] Strategies for multi-core speedups", by
- 2018.01.15 23:29 "Re: [Tiff] Strategies for multi-core speedups", by Larry Gritz
- 2018.01.16 18:48 "Re: [Tiff] Strategies for multi-core speedups", by scott ribe
- 2018.01.16 19:01 "Re: [Tiff] Strategies for multi-core speedups", by Kemp Watson
- 2018.01.16 19:34 "Re: [Tiff] Strategies for multi-core speedups", by Paavo Helde
-
2018.01.16 18:36 "Re: [Tiff] Strategies for multi-core speedups", by
-
2018.01.15 21:41 "Re: [Tiff] Strategies for multi-core speedups", by Larry Gritz
- 2018.01.16 20:18 "Re: [Tiff] Strategies for multi-core speedups", by Kemp Watson
- 2018.01.16 20:23 "Re: [Tiff] Strategies for multi-core speedups", by
-
2018.01.16 00:15 "Re: [Tiff] Strategies for multi-core speedups", by Bob Friesenhahn
2018.01.16 00:43 "Re: [Tiff] Strategies for multi-core speedups", by Paul Hemmer
Very interesting to read this discussion!
> On Jan 15, 2018, at 7:30 PM, Bob Friesenhahn <bfriesen@simple.dallas.tx.us> wrote:
>
>> On Mon, 15 Jan 2018, Larry Gritz wrote:
>>
There is no mystery here -- the I/O itself is still serialized, so if it's only 10% of the total runtime, say, even perfectly linear thread scaling and an unlimited number of cores without any lock contention will experience a maximum of 10x improvement. Amdahl's Law and all that. That effect alone adequately explains my lack of thread scalability beyond 8 or so cores, for this application.
The I/O is not necessarily serialized. When using mmap, pread/pwrite, or asynchronous I/O, the I/O can also benefit from multi-threading given that the underlying storage is a multi-disk array or SSDs using PCIe NVMe (capable of up to 1024 simultaneous I/Os).
Amdahl's Law still applies. :-)
> bfriesen@simple.dallas.tx.us, https://eur03.safelinks.protection.outlook.com/?url=http%3A%2F%2Fwww.simplesystems.org%2Fusers%2Fbfriesen%2F&data=02%7C01%7C%7C884284da4ded44509cae08d55c784a86%7C84df9e7fe9f640afb435aaaaaaaaaaaa%7C1%7C0%7C636516594072892406&sdata=anY9qhnjanVD%2FcBa0OQ2eAy76wUG%2FfmfgJG86ius0ug%3D&reserved=0 > GraphicsMagick Maintainer, https://eur03.safelinks.protection.outlook.com/?url=http%3A%2F%2Fwww.GraphicsMagick.org%2F&data=02%7C01%7C%7C884284da4ded44509cae08d55c784a86%7C84df9e7fe9f640afb435aaaaaaaaaaaa%7C1%7C0%7C636516594072892406&sdata=buwfw5uyzKn8WUC6hm%2FGGMbDtkYECwSV9Qg%2BvSAccvY%3D&reserved=0
> https://eur03.safelinks.protection.outlook.com/?url=http%3A%2F%2Flists.maptools.org%2Fmailman%2Flistinfo%2Ftiff&data=02%7C01%7C%7C884284da4ded44509cae08d55c784a86%7C84df9e7fe9f640afb435aaaaaaaaaaaa%7C1%7C0%7C636516594072892406&sdata=QYLnG2XEbmBEzZ6CJsIQXnKKodDocvrXKsHHpEPUZvo%3D&reserved=0
> https://eur03.safelinks.protection.outlook.com/?url=http%3A%2F%2Fwww.remotesensing.org%2Flibtiff%2F&data=02%7C01%7C%7C884284da4ded44509cae08d55c784a86%7C84df9e7fe9f640afb435aaaaaaaaaaaa%7C1%7C0%7C636516594072892406&sdata=%2FQiXDn3i%2FkawMaJg%2F0GuKGU1%2FwkLMwLtWUt6908mFrY%3D&reserved=0