|
1)
Message boards :
Number crunching :
Dependence on the size of L3 cache on multi tread Amd and Intel CPU
(Message 4162)
Posted 24 days ago by Shmya-2 Post: Noticing a dependency on the L3 cache size and CPU time with HT tasks. More L3 cache is more important than CPU frequency. As example: AMD chip with higher frequency and with 8 mb L3 is slower than AMD chip 16 L3 (within similar mobile architecture and generation r5 5300u/r5 7430u/r5 4600 (desktop but based on mobile chip) |
|
2)
Message boards :
Number crunching :
Gerasim is not working
(Message 4116)
Posted 22 Dec 2025 by Shmya-2 Post: Сентябрьские задания загрузились? |
|
3)
Message boards :
News :
Batch plan
(Message 4114)
Posted 21 Dec 2025 by Shmya-2 Post: Approximately 800,000,000 wu to do until project finish/end goal.... With current production rate (about 80-100 thousands per day) we will finish crunch race in 2050.... |
|
4)
Message boards :
Number crunching :
Shmya-2 Cluster upgrade
(Message 4054)
Posted 3 Nov 2025 by Shmya-2 Post: I am going to upgrade team's cluster in next two months. I choose between add more CPU miniPC machines (i5-10400 or ryzen 5 3600) and multi 8x GPU (CH70X GTX 3070ti mining card). Question: CPU or GPU will be better for Number Fields? |
|
5)
Message boards :
Number crunching :
CPU HT and batch
(Message 3975)
Posted 13 Sep 2025 by Shmya-2 Post: Two years ago Prescott wrote about CPU HT task time "Hi! I was not able to find an answer so I am posting here to ask! I know some projects discourage Hyper-threading on CPU's for certain tasks because it makes them slower/produce bad results. Excluding the issues from heat generation from HT, is there a problem with using HT for this project? Best, Prescott" At the end of discussion Prescott summarise posts: 58% longer time on each task with HT. My two days small experiment result is 47-100% longer task time with HT and all cores run on r5 3600, i5-10400f, r5 5300u. |