From WikiChip
Difference between revisions of "intel/xeon phi/7295"
(7 intermediate revisions by 3 users not shown) | |||
Line 13: | Line 13: | ||
|first announced=December 18, 2017 | |first announced=December 18, 2017 | ||
|first launched=December 18, 2017 | |first launched=December 18, 2017 | ||
+ | |last order=August 9, 2019 | ||
+ | |last shipment=July 31, 2020 | ||
|family=Xeon Phi | |family=Xeon Phi | ||
|series=x205 | |series=x205 | ||
Line 33: | Line 35: | ||
|v core max=1.2 V | |v core max=1.2 V | ||
|tdp=320 W | |tdp=320 W | ||
− | |tcase min= | + | |tcase min=5 °C |
|tcase max=77 °C | |tcase max=77 °C | ||
− | |package | + | |dts min=5 °C |
+ | |dts max=94 °C | ||
+ | |package name 1=intel,fclga_3647 | ||
}} | }} | ||
'''Xeon Phi 7295''' is a 72-core [[x86]] [[many-core microprocessor]] introduced by [[Intel]] in late [[2017]] specifically designed to [[accelerator|accelerate]] artificial intelligence workloads. This processor, which is fabricated on their own [[14 nm process]] based on the {{intel|Knights Mill|l=arch}} microarchitecture, operates at a frequency of 1.5 GHz with a TDP of 320 W and a turbo of 1.6 GHz. | '''Xeon Phi 7295''' is a 72-core [[x86]] [[many-core microprocessor]] introduced by [[Intel]] in late [[2017]] specifically designed to [[accelerator|accelerate]] artificial intelligence workloads. This processor, which is fabricated on their own [[14 nm process]] based on the {{intel|Knights Mill|l=arch}} microarchitecture, operates at a frequency of 1.5 GHz with a TDP of 320 W and a turbo of 1.6 GHz. | ||
Line 56: | Line 60: | ||
|l2 break=36x1 MiB | |l2 break=36x1 MiB | ||
|l2 desc=16-way set associative | |l2 desc=16-way set associative | ||
+ | }} | ||
+ | |||
+ | == Memory controller == | ||
+ | {{memory controller | ||
+ | |type=DDR4-2400 | ||
+ | |ecc=Yes | ||
+ | |max mem=384 GiB | ||
+ | |controllers=2 | ||
+ | |channels=6 | ||
+ | |max bandwidth=107.3 GiB/s | ||
+ | |bandwidth schan=17.88 GiB/s | ||
+ | |bandwidth dchan=35.76 GiB/s | ||
+ | |bandwidth qchan=71.53 GiB/s | ||
+ | |bandwidth hchan=107.3 GiB/s | ||
+ | }} | ||
+ | |||
+ | == Expansions == | ||
+ | {{expansions main | ||
+ | | | ||
+ | {{expansions entry | ||
+ | |type=PCIe | ||
+ | |pcie revision=3.0 | ||
+ | |pcie lanes=36 | ||
+ | |pcie config=x16 | ||
+ | |pcie config 2=x8 | ||
+ | |pcie config 3=x4 | ||
+ | |pcie config 4=x2 | ||
+ | |pcie config 5=x1 | ||
+ | }} | ||
+ | }} | ||
+ | |||
+ | == Features == | ||
+ | {{x86 features | ||
+ | |real=Yes | ||
+ | |protected=Yes | ||
+ | |smm=Yes | ||
+ | |fpu=Yes | ||
+ | |x8616=Yes | ||
+ | |x8632=Yes | ||
+ | |x8664=Yes | ||
+ | |nx=Yes | ||
+ | |mmx=Yes | ||
+ | |emmx=Yes | ||
+ | |sse=Yes | ||
+ | |sse2=Yes | ||
+ | |sse3=Yes | ||
+ | |ssse3=Yes | ||
+ | |sse41=Yes | ||
+ | |sse42=Yes | ||
+ | |sse4a=No | ||
+ | |avx=Yes | ||
+ | |avx2=Yes | ||
+ | |avx512f=Yes | ||
+ | |avx512cd=Yes | ||
+ | |avx512er=Yes | ||
+ | |avx512pf=Yes | ||
+ | |avx512bw=No | ||
+ | |avx512dq=No | ||
+ | |avx512vl=No | ||
+ | |avx512ifma=No | ||
+ | |avx512vbmi=No | ||
+ | |avx5124fmaps=Yes | ||
+ | |avx5124vnniw=Yes | ||
+ | |avx512vpopcntdq=Yes | ||
+ | |abm=Yes | ||
+ | |tbm=No | ||
+ | |bmi1=Yes | ||
+ | |bmi2=Yes | ||
+ | |fma3=Yes | ||
+ | |fma4=No | ||
+ | |aes=Yes | ||
+ | |rdrand=Yes | ||
+ | |sha=No | ||
+ | |xop=No | ||
+ | |adx=No | ||
+ | |clmul=Yes | ||
+ | |f16c=Yes | ||
+ | |tbt1=No | ||
+ | |tbt2=Yes | ||
+ | |tbmt3=No | ||
+ | |bpt=No | ||
+ | |eist=No | ||
+ | |sst=No | ||
+ | |flex=No | ||
+ | |fastmem=No | ||
+ | |ivmd=No | ||
+ | |intelnodecontroller=No | ||
+ | |intelnode=No | ||
+ | |kpt=No | ||
+ | |ptt=No | ||
+ | |intelrunsure=No | ||
+ | |mbe=No | ||
+ | |isrt=No | ||
+ | |sba=No | ||
+ | |mwt=No | ||
+ | |sipp=No | ||
+ | |att=No | ||
+ | |ipt=No | ||
+ | |tsx=No | ||
+ | |txt=No | ||
+ | |ht=Yes | ||
+ | |vpro=No | ||
+ | |vtx=Yes | ||
+ | |vtd=Yes | ||
+ | |ept=Yes | ||
+ | |mpx=No | ||
+ | |sgx=No | ||
+ | |securekey=No | ||
+ | |osguard=No | ||
+ | |intqat=No | ||
+ | |3dnow=No | ||
+ | |e3dnow=No | ||
+ | |smartmp=No | ||
+ | |powernow=No | ||
+ | |amdvi=No | ||
+ | |amdv=No | ||
+ | |amdsme=No | ||
+ | |amdtsme=No | ||
+ | |amdsev=No | ||
+ | |rvi=No | ||
+ | |smt=No | ||
+ | |sensemi=No | ||
+ | |xfr=No | ||
+ | |mxfr=No | ||
+ | |amdpb=No | ||
+ | |amdpb2=No | ||
}} | }} |
Latest revision as of 09:28, 10 May 2019
Edit Values | |
Xeon Phi 7295 | |
General Info | |
Designer | Intel |
Manufacturer | Intel |
Model Number | 7295 |
Part Number | HJ8068303823700 |
S-Spec | SR3VD |
Market | Workstation, Server, Supercomputer |
Introduction | December 18, 2017 (announced) December 18, 2017 (launched) |
End-of-life | August 9, 2019 (last order) July 31, 2020 (last shipment) |
Shop | Amazon |
General Specs | |
Family | Xeon Phi |
Series | x205 |
Locked | Yes |
Frequency | 1,500 MHz |
Turbo Frequency | 1,600 MHz (1 core) |
Clock multiplier | 15 |
Microarchitecture | |
ISA | x86-64 (x86) |
Microarchitecture | Knights Mill |
Core Stepping | A0 |
Process | 14 nm |
Technology | CMOS |
Word Size | 64 bit |
Cores | 72 |
Threads | 288 |
Max Memory | 384 GiB |
Multiprocessing | |
Max SMP | 1-Way (Uniprocessor) |
Electrical | |
Vcore | 0.55 V-1.2 V |
TDP | 320 W |
Tcase | 5 °C – 77 °C |
TDTS | 5 °C – 94 °C |
Packaging | |
Package | FCLGA-3647 (FCLGA) |
Dimension | 76.16 mm × 56.6 mm |
Pitch | 0.8585 mm × 0.9906 mm |
Contacts | 3647 |
Socket | Socket P, LGA-3647 |
Xeon Phi 7295 is a 72-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 1.5 GHz with a TDP of 320 W and a turbo of 1.6 GHz.
Contents
Cache[edit]
- Main article: Knights Mill § Cache
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. |
|||||||||||||||||||||||||
|
Memory controller[edit]
Integrated Memory Controller
|
||||||||||||||
|
Expansions[edit]
Expansion Options |
|||||
|
Features[edit]
[Edit/Modify Supported Features]
Facts about "Xeon Phi 7295 - Intel"
Has subobject "Has subobject" is a predefined property representing a container construct and is provided by Semantic MediaWiki. | Xeon Phi 7295 - Intel#pcie + |
base frequency | 1,500 MHz (1.5 GHz, 1,500,000 kHz) + |
clock multiplier | 15 + |
core count | 72 + |
core stepping | A0 + |
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) + |
designer | Intel + |
family | Xeon Phi + |
first announced | December 18, 2017 + |
first launched | December 18, 2017 + |
full page name | intel/xeon phi/7295 + |
has advanced vector extensions | true + |
has advanced vector extensions 2 | true + |
has advanced vector extensions 512 | true + |
has ecc memory support | true + |
has extended page tables support | true + |
has feature | Advanced Vector Extensions +, Advanced Vector Extensions 2 +, Advanced Vector Extensions 512 +, Advanced Encryption Standard Instruction Set Extension +, Hyper-Threading Technology +, Turbo Boost Technology 2.0 +, Intel VT-x +, Intel VT-d + and Extended Page Tables + |
has intel turbo boost technology 2 0 | true + |
has intel vt-d technology | true + |
has intel vt-x technology | true + |
has locked clock multiplier | true + |
has second level address translation support | true + |
has simultaneous multithreading | true + |
has x86 advanced encryption standard instruction set extension | true + |
instance of | microprocessor + |
isa | x86-64 + |
isa family | x86 + |
l1$ size | 4,608 KiB (4,718,592 B, 4.5 MiB) + |
l1d$ description | 8-way set associative + |
l1d$ size | 2,304 KiB (2,359,296 B, 2.25 MiB) + |
l1i$ description | 8-way set associative + |
l1i$ size | 2,304 KiB (2,359,296 B, 2.25 MiB) + |
l2$ description | 16-way set associative + |
l2$ size | 36 MiB (36,864 KiB, 37,748,736 B, 0.0352 GiB) + |
last order | August 9, 2019 + |
last shipment | July 31, 2020 + |
ldate | December 18, 2017 + |
main image | + |
manufacturer | Intel + |
market segment | Workstation +, Server + and Supercomputer + |
max case temperature | 350.15 K (77 °C, 170.6 °F, 630.27 °R) + |
max cpu count | 1 + |
max dts temperature | 94 °C + |
max memory | 393,216 MiB (402,653,184 KiB, 412,316,860,416 B, 384 GiB, 0.375 TiB) + |
max memory bandwidth | 107.3 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 channels | 6 + |
microarchitecture | Knights Mill + |
min case temperature | 278.15 K (5 °C, 41 °F, 500.67 °R) + |
min dts temperature | 5 °C + |
model number | 7295 + |
name | Xeon Phi 7295 + |
package | FCLGA-3647 + |
part number | HJ8068303823700 + |
process | 14 nm (0.014 μm, 1.4e-5 mm) + |
s-spec | SR3VD + |
series | x205 + |
smp max ways | 1 + |
socket | Socket P + and LGA-3647 + |
supported memory type | DDR4-2400 + |
tdp | 320 W (320,000 mW, 0.429 hp, 0.32 kW) + |
technology | CMOS + |
thread count | 288 + |
turbo frequency (1 core) | 1,600 MHz (1.6 GHz, 1,600,000 kHz) + |
word size | 64 bit (8 octets, 16 nibbles) + |