qcmadness

http://www.anandtech.com/show/11 ... attle-of-the-decade

Xeon

Sandbo

The database test ... How much did Anandtech receive for it?

qcmadness

引用:

原帖由 Sandbo 於 2017-7-13 01:26 發表
The database test ... How much did Anandtech receive for it?

I don't think so.
The database / transaction server is still in Xeon territories due to latency issues.

Sandbo

引用:

原帖由 qcmadness 於 2017-7-13 01:27 發表

I don't think so.
The database / transaction server is still in Xeon territories due to latency issues.

If you read the top comments, you will see (as in the article they also mentioned),
they chose "A small database that can be mostly cached in the L3-cache", which is largely not true for realistic scenarios.

qcmadness

引用:

原帖由 Sandbo 於 2017-7-13 01:32 發表

If you read the top comments, you will see (as in the article they also mentioned),
they chose "A small database that can be mostly cached in the L3-cache", which is largely not true for realistic sc ...

But even the database is stored in memory, the latency issues still remain.
You could think of some bias but the latency difference is still too large to ignore.

Sandbo

引用:

原帖由 qcmadness 於 2017-7-13 01:33 發表

But even the database is stored in memory, the latency issues still remain.
You could think of some bias but the latency difference is still too large to ignore.

Not sure, but if as comments mentioned (I don't know much about database) a real-life model requires data stored mostly in RAM,
EPYC has a much better bandwidth comparing to Intel's.

引用:

So the dual socket AMD system should theoretically get 307 GB per second (2.4 GT/s* 8 bytes per channel x 8 channels x 2 sockets). The Intel system has access to 256 GB per second (2.66 GT/s* 8 bytes per channel x 6 channels x 2 sockets).

So it is interesting (and probably more useful) to test a large database.

qcmadness

引用:

原帖由 Sandbo 於 2017-7-13 01:41 發表

Not sure, but if as comments mentioned (I don't know much about database) a real-life model requires data stored mostly in RAM,
EPYC has a much better bandwidth comparing to Intel's.



So it is inte ...

You will need to access other die's memory controller to get the data.

XT

tat0801

引用:

原帖由 XT 於 2017-7-14 02:00 發表
http://images.anandtech.com/graphs/graph11544/87247.png

AMD 呢次玩膠水8春反擊到Intel 無曬法子咁既？
又睇下威到幾時？
當年AMD 都係係K8 對P4 2.8e 果期叫好左一陣
C2D 一出就死直
果度三年唔夠

qcmadness

引用:

原帖由 tat0801 於 2017-7-14 19:47 發表

AMD 呢次玩膠水8春反擊到Intel 無曬法子咁既？
又睇下威到幾時？
當年AMD 都係係K8 對P4 2.8e 果期叫好左一陣
C2D 一出就死直
果度三年唔夠

之前仲有K7

不過Intel駛橫手

dom

引用:

原帖由 tat0801 於 14-7-2017 19:47 發表

AMD 呢次玩膠水8春反擊到Intel 無曬法子咁既？
又睇下威到幾時？
當年AMD 都係係K8 對P4 2.8e 果期叫好左一陣
C2D 一出就死直
果度三年唔夠

Well I am using Intel

tat0801

引用:

原帖由 dom 於 2017-7-16 04:28 發表


Well I am using Intel

家下Samsung 點算先？
啲LPDDR4 就黎變samsung 獨家
仲有啲64 layer 3d nand 又係佢

qcmadness

引用:

原帖由 tat0801 於 2017-7-16 10:58 發表

家下Samsung 點算先？
啲LPDDR4 就黎變samsung 獨家
仲有啲64 layer 3d nand 又係佢

全球市值最大果間科技公司係邊間?

tat0801

引用:

原帖由 qcmadness 於 2017-7-16 16:25 發表

全球市值最大果間科技公司係邊間?

呢次supply chain 出事唔多關生果事，而家Samsung 有絕大部分定價權下，其它廠死先咁解