amd cpu&gpu 討論post #7

係2700x前你都係

ces zen 2 es Sample



8c16t
base 3.7 ghz
boost 未知 （ 應該高於4.3ghz ）
tdp 65w

http://www.moepc.net/?post=5161#R3000

12c24t?

12c果個 早期 es來

即係之前個張5ghz係流料

65W有3.7Ghz
5Ghz唔一定流

超cpu會快d壞cpu？

amd 仲有 時間 調整 tdp （ 65w/95w/105w )

只要你比到一個合適既電壓 不會過低/過高 正常 cpu 會壞既機率好低

G.Skill Announces AMD X399-optimized DDR4-3466 32GB (4x8GB) Trident-Z Kit

G.SKILL International Enterprise Co., Ltd., the world's leading manufacturer of extreme performance memory and gaming peripherals, is excited to announce a new memory specification of DDR4-3466 CL18-22-22-42 with 32GB (4x8GB) capacity configuration at 1.35V for the high performance AMD Ryzen Threadripper processor and X399 platform. This memory kit will join the G.SKILL "Trident Z RGB (for AMD)" series, also known as the TZRX models.

Previously, the highest DDR4 speed available for the AMD X399 platform from G.SKILL was DDR4-3200. G.SKILL is now expanding the specifications to DDR4-3466 under the quad-channel configuration. This kit has been validated with the ASUS ROG ZENITH EXTREME ALPHA motherboard and AMD Ryzen Threadripper 2950X processor, as shown in the screenshots below.



https://www.techpowerup.com/251505/g-skill-announces-amd-x399-optimized-ddr4-3466-32gb-4x8gb-trident-z-kit

16*2呢屌

AMD Radeon VII Interview with Scott Herkelman

TDP : 300W
Power Connect : 2 x 8 pin
Where Can Buy : AMD.com ( limited ) / AIB / Dell Alienware 51
HDMI version : 2.0
Target : Content Creators

https://www.hardocp.com/article/2019/01/14/amd_radeon_vii_interview_scott_herkelman/1

更新 ： Radeon VII 不會有非公版

2700x @ ASUS X470-F
1.4v @ 4.2GHz
1.35v @ 2800MHz
暫穩定，聽日試下降壓去1.38v test 4.2GHz
Gen 3 Ryzen快d出啦，等緊7nm 16核5GHz

你用1.35v上到4.25已經要偷笑
仲計溫度做乜
進取d，再加壓上4.5GHz

得 Z？
Royal 呢？

zen+ 上 4.5 怕怕

唔知都會壞
識人普通用都可以壞左粒skylake嘅Celeron

wtf

AMD Comments on Threadripper 2 Performance and Windows Scheduler



Users may have been following Wendell from Level1Tech’s battle with researching the reasons behind why some benchmarks have regressed performance on quad-die Threadripper 2 compared to dual-die configurations. Through his research, he found that this problem was limited to Windows, as cross-platform software on Linux did not have this issue, and that the problem was not limited just to Threadripper 2, but quad-die EPYCs were also affected.

AMD Comments On The Findings

AMD stated that they have support and update tickets open with Microsoft’s Windows team on the issue. They believe they know what the issue is, and commends Wendell for being very close to what the actual issue is (they declined to go into detail). They are currently comparing notes with Bitsum, and actually helped Bitsum to develop the original tool for affinity masking, however the ‘NUMA Disassociator’ is obviously new.

The timeline for a fix will depend on a number of factors between AMD and Microsoft, however there will be announcements when the fix is ready and what exactly that fix will affect performance. Other improvements to help optimize performance will also be included. AMD is still very pleased with the Threadripper 2 performance, and is keen to stress that for the most popular performance related tests the company points to reviews that show that the performance in rendering is still well above the competition, and is working with software vendors to push that performance even further.

https://www.anandtech.com/show/13853/amd-comments-on-threadripper-2-performance-and-windows-scheduler

留意 ：



Anandtech 分別在 Epyc 和 Threadripper 平台做測試 （ 使用CorePrio /不使用CorePrio ）

結論 ： CorePrio is a good temporary solution for sure, however it needs to be fixed in the Windows scheduler.