From WikiChip
Xeon Phi 7235 - Intel
< intel‎ | xeon phi
Revision as of 20:05, 18 December 2017 by At32Hz (talk | contribs)

Edit Values
Xeon Phi 7235
xeon phi knights mill (front).png
General Info
DesignerIntel
ManufacturerIntel
Model Number7235
Part NumberHJ8068303823900
S-SpecSR3VF
MarketWorkstation, Server, Supercomputer
IntroductionDecember 18, 2017 (announced)
December 18, 2017 (launched)
ShopAmazon
General Specs
FamilyXeon Phi
Seriesx205
LockedYes
Frequency1,300 MHz
Turbo Frequency1,400 MHz (1 core)
Clock multiplier15
Microarchitecture
ISAx86-64 (x86)
MicroarchitectureKnights Mill
Core SteppingA0
Process14 nm
TechnologyCMOS
Word Size64 bit
Cores64
Threads256
Max Memory384 GiB
Multiprocessing
Max SMP1-Way (Uniprocessor)
Electrical
Vcore0.55 V-1.2 V
TDP250 W
Tcase0 °C – 77 °C
Packaging
Template:packages/intel/fclga-3647

Xeon Phi 7235 is a 64-core x86 many-core microprocessor introduced by Intel in late 2017 specifically designed to accelerate artificial intelligence workloads. This processor, which is fabricated on their own 14 nm process based on the Knights Mill microarchitecture, operates at a frequency of 1.3 GHz with a TDP of 250 W and a turbo of 1.4 GHz.


DIL16 Blank.svg Preliminary Data! Information presented in this article deal with a microprocessor or chip that was recently announced or leaked, thus missing information regarding its features and exact specification. Information may be incomplete and can change by final release.


Cache

Main article: Knights Mill § Cache

[Edit/Modify Cache Info]

hierarchy icon.svg
Cache Organization
Cache is a hardware component containing a relatively small and extremely fast memory designed to speed up the performance of a CPU by preparing ahead of time the data it needs to read from a relatively slower medium such as main memory.

The organization and amount of cache can have a large impact on the performance, power consumption, die size, and consequently cost of the IC.

Cache is specified by its size, number of sets, associativity, block size, sub-block size, and fetch and write-back policies.

Note: All units are in kibibytes and mebibytes.
L1$4 MiB
4,096 KiB
4,194,304 B
L1I$2 MiB
2,048 KiB
2,097,152 B
64x32 KiB8-way set associative 
L1D$2 MiB
2,048 KiB
2,097,152 B
64x32 KiB8-way set associative 

L2$32 MiB
32,768 KiB
33,554,432 B
0.0313 GiB
  32x1 MiB16-way set associative 

Memory controller

[Edit/Modify Memory Info]

ram icons.svg
Integrated Memory Controller
Max TypeDDR4-2400
Supports ECCYes
Max Mem384 GiB
Controllers2
Channels6
Max Bandwidth107.3 GiB/s
109,875.2 MiB/s
115.212 GB/s
115,212.498 MB/s
0.105 TiB/s
0.115 TB/s
Bandwidth
Single 17.88 GiB/s
Double 35.76 GiB/s
Quad 71.53 GiB/s
Hexa 107.3 GiB/s
Facts about "Xeon Phi 7235 - Intel"
base frequency1,300 MHz (1.3 GHz, 1,300,000 kHz) +
clock multiplier15 +
core count64 +
core steppingA0 +
core voltage (max)1.2 V (12 dV, 120 cV, 1,200 mV) +
core voltage (min)0.55 V (5.5 dV, 55 cV, 550 mV) +
designerIntel +
familyXeon Phi +
first announcedDecember 18, 2017 +
first launchedDecember 18, 2017 +
full page nameintel/xeon phi/7235 +
has ecc memory supporttrue +
has locked clock multipliertrue +
instance ofmicroprocessor +
isax86-64 +
isa familyx86 +
l1$ size4,096 KiB (4,194,304 B, 4 MiB) +
l1d$ description8-way set associative +
l1d$ size2,048 KiB (2,097,152 B, 2 MiB) +
l1i$ description8-way set associative +
l1i$ size2,048 KiB (2,097,152 B, 2 MiB) +
l2$ description16-way set associative +
l2$ size32 MiB (32,768 KiB, 33,554,432 B, 0.0313 GiB) +
ldateDecember 18, 2017 +
main imageFile:xeon phi knights mill (front).png +
manufacturerIntel +
market segmentWorkstation +, Server + and Supercomputer +
max case temperature350.15 K (77 °C, 170.6 °F, 630.27 °R) +
max cpu count1 +
max memory393,216 MiB (402,653,184 KiB, 412,316,860,416 B, 384 GiB, 0.375 TiB) +
max memory bandwidth107.3 GiB/s (109,875.2 MiB/s, 115.212 GB/s, 115,212.498 MB/s, 0.105 TiB/s, 0.115 TB/s) +
max memory channels6 +
microarchitectureKnights Mill +
min case temperature273.15 K (0 °C, 32 °F, 491.67 °R) +
model number7235 +
nameXeon Phi 7235 +
part numberHJ8068303823900 +
process14 nm (0.014 μm, 1.4e-5 mm) +
s-specSR3VF +
seriesx205 +
smp max ways1 +
supported memory typeDDR4-2400 +
tdp250 W (250,000 mW, 0.335 hp, 0.25 kW) +
technologyCMOS +
thread count256 +
turbo frequency (1 core)1,400 MHz (1.4 GHz, 1,400,000 kHz) +
word size64 bit (8 octets, 16 nibbles) +