From WikiChip
Difference between revisions of "intel/xeon gold/5117"
< intel‎ | xeon gold

m (Bot: Automated text replacement (-|avx512=Yes +))
(13 intermediate revisions by 3 users not shown)
Line 1: Line 1:
 
{{intel title|Xeon Gold 5117}}
 
{{intel title|Xeon Gold 5117}}
{{mpu
+
{{chip
|future=Yes
 
 
|name=Xeon Gold 5117
 
|name=Xeon Gold 5117
|no image=Yes
+
|image=skylake sp (basic).png
 
|designer=Intel
 
|designer=Intel
 
|manufacturer=Intel
 
|manufacturer=Intel
 
|model number=5117
 
|model number=5117
 +
|s-spec qs=QM8S
 
|market=Server
 
|market=Server
|first announced=April 25, 2017
+
|first announced=July 11, 2017
 +
|first launched=July 11, 2017
 
|family=Xeon Gold
 
|family=Xeon Gold
|series=5000
+
|series=5100
 
|locked=Yes
 
|locked=Yes
|frequency=2.0 GHz
+
|frequency=2,000 MHz
|bus type=DMI 3.0
+
|turbo frequency1=2,800 MHz
|bus links=4
 
|bus rate=8 GT/s
 
 
|clock multiplier=20
 
|clock multiplier=20
 +
|cpuid=0x50654
 
|isa=x86-64
 
|isa=x86-64
 
|isa family=x86
 
|isa family=x86
|microarch=Skylake
+
|microarch=Skylake (server)
 
|platform=Purley
 
|platform=Purley
 
|chipset=Lewisburg
 
|chipset=Lewisburg
 
|core name=Skylake SP
 
|core name=Skylake SP
 
|core family=6
 
|core family=6
|core stepping=H0
 
 
|process=14 nm
 
|process=14 nm
 
|technology=CMOS
 
|technology=CMOS
|die area=<!-- XX mm² -->
 
 
|word size=64 bit
 
|word size=64 bit
 
|core count=14
 
|core count=14
 
|thread count=28
 
|thread count=28
|max cpus=2
+
|max cpus=4
|v core tolerance=<!-- OR ... -->
+
|max memory=768 GiB
|v io 2=<!-- OR ... -->
+
|tdp=105 W
|temp min=<!-- use TJ/TC whenever possible instead -->
+
|tcase min=0 °C
|tjunc min=<!-- .. °C -->
+
|tcase max=81 °C
|package module 2=<!-------- USE ONLY IF MUST, OTHERWISE TRY TO USE MODULE ABOVE -------------->
+
|package name 1=intel,fclga_3647
|package module 1={{packages/intel/fclga-3647}}
+
|successor=Xeon Gold 5217
 +
|successor link=intel/xeon_gold/5217
 
}}
 
}}
'''Xeon Gold 5117''' is a {{arch|64}} [[x86]] high-performance server [[tetradeca-core]] [[multiprocessor]] set to be introduced by [[Intel]] in the second quarter of 2017. This processor is based on the server configuration of the {{intel|Skylake|l=arch}} microarchitecture (a {{intel|Skylake SP|l=core}} core) and is manufactured on Intel's [[14 nm process]]. The 5117 operates at 2 GHz.
+
'''Xeon Gold 5117''' is a {{arch|64}} [[tetradeca-core]] [[x86]] multi-socket high performance server microprocessor introduced by [[Intel]] in mid-2017. This chip supports up to 4-way multiprocessing. The Gold 5117, which is based on the server configuration of the {{intel|Skylake (server)|Skylake|l=arch}} microarchitecture and is manufactured on a [[14 nm process|14 nm+ process]], sports 1 {{x86|AVX-512}} [[FMA]] unit as well as three {{intel|Ultra Path Interconnect}} links. This microprocessor, which operates at 2 GHz with a TDP of 105 W and a {{intel|turbo boost}} frequency of up to 2.8 GHz, supports up 768 GiB of hexa-channel DDR4-2400 ECC memory.
 
 
 
 
{{unknown features}}
 
  
 
== Cache ==
 
== Cache ==
{{main|intel/microarchitectures/skylake#Memory_Hierarchy|l1=Skylake § Cache}}
+
{{main|intel/microarchitectures/skylake_(server)#Memory_Hierarchy|l1=Skylake § Cache}}
 
{{cache size
 
{{cache size
 
|l1 cache=896 KiB
 
|l1 cache=896 KiB
Line 52: Line 48:
 
|l1i desc=8-way set associative
 
|l1i desc=8-way set associative
 
|l1d cache=448 KiB
 
|l1d cache=448 KiB
|l1d break=28x32 KiB
+
|l1d break=14x32 KiB
 
|l1d desc=8-way set associative
 
|l1d desc=8-way set associative
 
|l1d policy=write-back
 
|l1d policy=write-back
Line 67: Line 63:
 
== Memory controller ==
 
== Memory controller ==
 
{{memory controller
 
{{memory controller
|type=DDR4-2666
+
|type=DDR4-2400
 
|ecc=Yes
 
|ecc=Yes
|max mem=
+
|max mem=768 GiB
|controllers=1
+
|controllers=2
 
|channels=6
 
|channels=6
|max bandwidth=119.21 GiB/s
+
|max bandwidth=107.3 GiB/s
|bandwidth schan=19.89 GiB/s
+
|bandwidth schan=17.88 GiB/s
|bandwidth dchan=39.72 GiB/s
+
|bandwidth dchan=35.76 GiB/s
|bandwidth qchan=79.47 GiB/s
+
|bandwidth qchan=71.53 GiB/s
|bandwidth hchan=119.21 GiB/s
+
|bandwidth hchan=107.3 GiB/s
 +
}}
 +
 
 +
== Expansions ==
 +
{{expansions
 +
| pcie revision      = 3.0
 +
| pcie lanes        = 48
 +
| pcie config        = x16
 +
| pcie config 2      = x8
 +
| pcie config 3      = x4
 
}}
 
}}
  
Line 100: Line 105:
 
|avx=Yes
 
|avx=Yes
 
|avx2=Yes
 
|avx2=Yes
 
+
|avx512f=Yes
 +
|avx512cd=Yes
 +
|avx512er=No
 +
|avx512pf=No
 +
|avx512bw=Yes
 +
|avx512dq=Yes
 +
|avx512vl=Yes
 +
|avx512ifma=No
 +
|avx512vbmi=No
 +
|avx5124fmaps=No
 +
|avx5124vnniw=No
 +
|avx512vpopcntdq=No
 
|abm=Yes
 
|abm=Yes
 
|tbm=No
 
|tbm=No
Line 115: Line 131:
 
|f16c=Yes
 
|f16c=Yes
 
|tbt1=No
 
|tbt1=No
|tbt2=No
+
|tbt2=Yes
 
|tbmt3=No
 
|tbmt3=No
 
|bpt=No
 
|bpt=No
 
|eist=Yes
 
|eist=Yes
|sst=No
+
|sst=Yes
 
|flex=No
 
|flex=No
 
|fastmem=No
 
|fastmem=No
 +
|ivmd=Yes
 +
|intelnode=Yes
 +
|kpt=Yes
 +
|ptt=Yes
 +
|mbe=Yes
 
|isrt=No
 
|isrt=No
 
|sba=No
 
|sba=No
Line 129: Line 150:
 
|ipt=No
 
|ipt=No
 
|tsx=Yes
 
|tsx=Yes
|txt=No
+
|txt=Yes
 
|ht=Yes
 
|ht=Yes
 
|vpro=Yes
 
|vpro=Yes
 
|vtx=Yes
 
|vtx=Yes
|vtd=Yes
+
|vtd=No
 
|ept=Yes
 
|ept=Yes
|mpx=Yes
+
|mpx=No
 
|sgx=No
 
|sgx=No
 
|securekey=No
 
|securekey=No
|osguard=Yes
+
|osguard=No
 
|3dnow=No
 
|3dnow=No
 
|e3dnow=No
 
|e3dnow=No
Line 145: Line 166:
 
|amdvi=No
 
|amdvi=No
 
|amdv=No
 
|amdv=No
 +
|amdsme=No
 +
|amdtsme=No
 +
|amdsev=No
 
|rvi=No
 
|rvi=No
 
|smt=No
 
|smt=No
Line 150: Line 174:
 
|xfr=No
 
|xfr=No
 
}}
 
}}
 +
 +
== Frequencies ==
 +
{{see also|intel/frequency_behavior|l1=Intel's CPU Frequency Behavior}}
 +
{{frequency table
 +
|freq_base=2,000 MHz
 +
|freq_1=2,800 MHz
 +
|freq_2=2,800 MHz
 +
|freq_3=2,600 MHz
 +
|freq_4=2,600 MHz
 +
|freq_5=2,500 MHz
 +
|freq_6=2,500 MHz
 +
|freq_7=2,500 MHz
 +
|freq_8=2,500 MHz
 +
|freq_9=2,400 MHz
 +
|freq_10=2,400 MHz
 +
|freq_11=2,400 MHz
 +
|freq_12=2,400 MHz
 +
|freq_13=2,300 MHz
 +
|freq_14=2,300 MHz
 +
|freq_avx2_base=1,300 MHz
 +
|freq_avx2_1=2,800 MHz
 +
|freq_avx2_2=2,800 MHz
 +
|freq_avx2_3=2,500 MHz
 +
|freq_avx2_4=2,500 MHz
 +
|freq_avx2_5=1,900 MHz
 +
|freq_avx2_6=1,900 MHz
 +
|freq_avx2_7=1,900 MHz
 +
|freq_avx2_8=1,900 MHz
 +
|freq_avx2_9=1,600 MHz
 +
|freq_avx2_10=1,600 MHz
 +
|freq_avx2_11=1,600 MHz
 +
|freq_avx2_12=1,600 MHz
 +
|freq_avx2_13=1,600 MHz
 +
|freq_avx2_14=1,600 MHz
 +
|freq_avx512_base=1,100 MHz
 +
|freq_avx512_1=2,800 MHz
 +
|freq_avx512_2=2,800 MHz
 +
|freq_avx512_3=2,200 MHz
 +
|freq_avx512_4=2,200 MHz
 +
|freq_avx512_5=1,700 MHz
 +
|freq_avx512_6=1,700 MHz
 +
|freq_avx512_7=1,700 MHz
 +
|freq_avx512_8=1,700 MHz
 +
|freq_avx512_9=1,400 MHz
 +
|freq_avx512_10=1,400 MHz
 +
|freq_avx512_11=1,400 MHz
 +
|freq_avx512_12=1,400 MHz
 +
|freq_avx512_13=1,400 MHz
 +
|freq_avx512_14=1,400 MHz
 +
}}
 +
 +
[[Category:microprocessor models by intel based on skylake extreme core count die]]

Revision as of 01:09, 24 May 2019

Edit Values
Xeon Gold 5117
skylake sp (basic).png
General Info
DesignerIntel
ManufacturerIntel
Model Number5117
S-SpecQM8S (QS)
MarketServer
IntroductionJuly 11, 2017 (announced)
July 11, 2017 (launched)
ShopAmazon
General Specs
FamilyXeon Gold
Series5100
LockedYes
Frequency2,000 MHz
Turbo Frequency2,800 MHz (1 core)
Clock multiplier20
CPUID0x50654
Microarchitecture
ISAx86-64 (x86)
MicroarchitectureSkylake (server)
PlatformPurley
ChipsetLewisburg
Core NameSkylake SP
Core Family6
Process14 nm
TechnologyCMOS
Word Size64 bit
Cores14
Threads28
Max Memory768 GiB
Multiprocessing
Max SMP4-Way (Multiprocessor)
Electrical
TDP105 W
Tcase0 °C – 81 °C
Packaging
PackageFCLGA-3647 (FCLGA)
Dimension76.16 mm × 56.6 mm
Pitch0.8585 mm × 0.9906 mm
Contacts3647
SocketSocket P, LGA-3647
Succession

Xeon Gold 5117 is a 64-bit tetradeca-core x86 multi-socket high performance server microprocessor introduced by Intel in mid-2017. This chip supports up to 4-way multiprocessing. The Gold 5117, which is based on the server configuration of the Skylake microarchitecture and is manufactured on a 14 nm+ process, sports 1 AVX-512 FMA unit as well as three Ultra Path Interconnect links. This microprocessor, which operates at 2 GHz with a TDP of 105 W and a turbo boost frequency of up to 2.8 GHz, supports up 768 GiB of hexa-channel DDR4-2400 ECC memory.

Cache

Main article: Skylake § 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$896 KiB
917,504 B
0.875 MiB
L1I$448 KiB
458,752 B
0.438 MiB
14x32 KiB8-way set associative 
L1D$448 KiB
458,752 B
0.438 MiB
14x32 KiB8-way set associativewrite-back

L2$14 MiB
14,336 KiB
14,680,064 B
0.0137 GiB
  14x1 MiB16-way set associativewrite-back

L3$19.25 MiB
19,712 KiB
20,185,088 B
0.0188 GiB
  14x1.375 MiB11-way set associativewrite-back

Memory controller

[Edit/Modify Memory Info]

ram icons.svg
Integrated Memory Controller
Max TypeDDR4-2400
Supports ECCYes
Max Mem768 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

Expansions

[Edit/Modify Expansions Info]

ide icon.svg
Expansion Options
PCIe
Revision3.0
Max Lanes48
Configsx16, x8, x4


Features

[Edit/Modify Supported Features]

Cog-icon-grey.svg
Supported x86 Extensions & Processor Features
MMXMMX Extension
EMMXExtended MMX Extension
SSEStreaming SIMD Extensions
SSE2Streaming SIMD Extensions 2
SSE3Streaming SIMD Extensions 3
SSSE3Supplemental SSE3
SSE4.1Streaming SIMD Extensions 4.1
SSE4.2Streaming SIMD Extensions 4.2
AVXAdvanced Vector Extensions
AVX2Advanced Vector Extensions 2
AVX-512Advanced Vector 512-bit
AVX512FAVX-512 Foundation
AVX512CDAVX-512 Conflict Detection
AVX512BWAVX-512 Byte and Word
AVX512DQAVX-512 Doubleword and Quadword Instructions
AVX512VLAVX-512 Vector Length
ABMAdvanced Bit Manipulation
BMI1Bit Manipulation Instruction Set 1
BMI2Bit Manipulation Instruction Set 2
FMA33-Operand Fused-Multiply-Add
AESAES Encryption Instructions
RdRandHardware RNG
ADXMulti-Precision Add-Carry
CLMULCarry-less Multiplication Extension
F16C16-bit Floating Point Conversion
x86-1616-bit x86
x86-3232-bit x86
x86-6464-bit x86
RealReal Mode
ProtectedProtected Mode
SMMSystem Management Mode
FPUIntegrated x87 FPU
NXNo-eXecute
HTHyper-Threading
TBT 2.0Turbo Boost Technology 2.0
EISTEnhanced SpeedStep Technology
SSTSpeed Shift Technology
TXTTrusted Execution Technology (SMX)
vProIntel vPro
VT-xVT-x (Virtualization)
EPTExtended Page Tables (SLAT)
TSXTransactional Synchronization Extensions
VMDVolume Management Device
NMNode Manager
KPTKey Protection Technology
PTTPlatform Trust Technology
MBE CtrlMode-Based Execute Control

Frequencies

See also: Intel's CPU Frequency Behavior

[Modify Frequency Info]

ModeBaseTurbo Frequency/Active Cores
1234567891011121314
Normal2,000 MHz2,800 MHz2,800 MHz2,600 MHz2,600 MHz2,500 MHz2,500 MHz2,500 MHz2,500 MHz2,400 MHz2,400 MHz2,400 MHz2,400 MHz2,300 MHz2,300 MHz
AVX21,300 MHz2,800 MHz2,800 MHz2,500 MHz2,500 MHz1,900 MHz1,900 MHz1,900 MHz1,900 MHz1,600 MHz1,600 MHz1,600 MHz1,600 MHz1,600 MHz1,600 MHz
AVX5121,100 MHz2,800 MHz2,800 MHz2,200 MHz2,200 MHz1,700 MHz1,700 MHz1,700 MHz1,700 MHz1,400 MHz1,400 MHz1,400 MHz1,400 MHz1,400 MHz1,400 MHz
Has subobject
"Has subobject" is a predefined property representing a container construct and is provided by Semantic MediaWiki.
Xeon Gold 5117 - Intel#io +
base frequency2,000 MHz (2 GHz, 2,000,000 kHz) +
chipsetLewisburg +
clock multiplier20 +
core count14 +
core family6 +
core nameSkylake SP +
cpuid0x50654 +
designerIntel +
familyXeon Gold +
first announcedJuly 11, 2017 +
first launchedJuly 11, 2017 +
full page nameintel/xeon gold/5117 +
has advanced vector extensionstrue +
has advanced vector extensions 2true +
has advanced vector extensions 512true +
has ecc memory supporttrue +
has extended page tables supporttrue +
has featureAdvanced Vector Extensions +, Advanced Vector Extensions 2 +, Advanced Vector Extensions 512 +, Advanced Encryption Standard Instruction Set Extension +, Hyper-Threading Technology +, Turbo Boost Technology 2.0 +, Enhanced SpeedStep Technology +, Speed Shift Technology +, Trusted Execution Technology +, Intel vPro Technology +, Intel VT-x +, Extended Page Tables + and Transactional Synchronization Extensions +
has intel enhanced speedstep technologytrue +
has intel speed shift technologytrue +
has intel trusted execution technologytrue +
has intel turbo boost technology 2 0true +
has intel vpro technologytrue +
has intel vt-x technologytrue +
has locked clock multipliertrue +
has second level address translation supporttrue +
has simultaneous multithreadingtrue +
has transactional synchronization extensionstrue +
has x86 advanced encryption standard instruction set extensiontrue +
instance ofmicroprocessor +
isax86-64 +
isa familyx86 +
l1$ size896 KiB (917,504 B, 0.875 MiB) +
l1d$ description8-way set associative +
l1d$ size448 KiB (458,752 B, 0.438 MiB) +
l1i$ description8-way set associative +
l1i$ size448 KiB (458,752 B, 0.438 MiB) +
l2$ description16-way set associative +
l2$ size14 MiB (14,336 KiB, 14,680,064 B, 0.0137 GiB) +
l3$ description11-way set associative +
l3$ size19.25 MiB (19,712 KiB, 20,185,088 B, 0.0188 GiB) +
ldateJuly 11, 2017 +
main imageFile:skylake sp (basic).png +
manufacturerIntel +
market segmentServer +
max case temperature354.15 K (81 °C, 177.8 °F, 637.47 °R) +
max cpu count4 +
max memory786,432 MiB (805,306,368 KiB, 824,633,720,832 B, 768 GiB, 0.75 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 +
max pcie lanes48 +
microarchitectureSkylake (server) +
min case temperature273.15 K (0 °C, 32 °F, 491.67 °R) +
model number5117 +
nameXeon Gold 5117 +
packageFCLGA-3647 +
platformPurley +
process14 nm (0.014 μm, 1.4e-5 mm) +
s-spec (qs)QM8S +
series5100 +
smp max ways4 +
socketSocket P + and LGA-3647 +
supported memory typeDDR4-2400 +
tdp105 W (105,000 mW, 0.141 hp, 0.105 kW) +
technologyCMOS +
thread count28 +
turbo frequency (1 core)2,800 MHz (2.8 GHz, 2,800,000 kHz) +
word size64 bit (8 octets, 16 nibbles) +