Intel Xeon Phi 3120P 

Released April, 2013
  • 1.1 GHz
  • 57 cores

The Coprocessor evolved from the following idea: A GPU is like ten thousand monkeys taught to do a single job while a CPU is like a group of 10 highly intelligent scientists.
by Syed-Muhammad-Usman-Pirzada (Nov, 2013)
So far it is much easier to employ multiple GPU Form Factors than Multiple Socket Processors/Coprocessors..
by Syed-Muhammad-Usman-Pirzada (Nov, 2013)

Features Key features of the Intel Xeon Phi 3120P

clock speed

Xeon Phi 3120P
1.1 GHz
Athlon X2 5200B
2.7 GHz
Xeon Phi 5110P
1.05 GHz

L2 cache

Xeon Phi 3120P
28.5 MB

TDP

Xeon Phi 3120P
300W

In The News From around the web

16GB Hybrid Memory Cube will Supercharge the 14nm ‘Knights Landing’ Intel Xeon Phi Co-Processors.
As you may recall the codename of the upcoming “Xeon Phi” Processors is ‘Knights Landing.
The Xeon Phi Co-Processor is a brute beast and Intel’s top of the line high-performance compute accelerator which has been integrated in the world’s fastest supercomputer, the Guangzhou’s Tianhe 2.
That is relatively higher compared to 16 GB featured on Knights Corner but we are comparing DDR4 against GDDR5 here.
And if you think that 3 Tera Flops of Double Precision is not alot then see this, Nvidia’s newest flagship the Tesla K40 only manages a bare 1.33 TF on DP.
Knights Landing will have around 72 cores.
However if Phi comes to the LGA Socket, it will loose GDDR5 and best case scenario have the DDR4 memory.
The Coprocessor evolved from the following idea: A GPU is like ten thousand monkeys taught to do a single job while a CPU is like a group of 10 highly intelligent scientists.

Specifications Full list of technical specs

summary

Clock speed 1.1 GHz
Cores 57 cores
Socket type PCI Express x16
Is unlocked No

features

Has a NX bit Yes
Supports trusted computing No
Has virtualization support No
Instruction set extensions FMA3
Supports dynamic frequency scaling No

memory controller

Memory controller Built-in
Memory type GDDR5
Channels Dual Channel
Supports ECC Yes
Maximum memory size 6,144 MB

details

Architecture x86-64
Threads 228 threads
L2 cache 28.5 MB
L2 cache per core 0.5 MB/core
Manufacture process 22 nm
Max CPUs 8

integrated graphics

GPU None

power consumption

TDP 300W
Annual home energy cost 72.27 $/year
Annual commercial energy cost 262.8 $/year
Typical power consumption 243.75W

bus

Architecture FSB
Report a correction

Comments

comments powered by Disqus