Difference between revisions of "intel/xeon silver/4108"

	Edit Values
	Xeon Silver 4108
	General Info
Designer	Intel
Manufacturer	Intel
Model Number	4108
Part Number	BX806734108,; CD8067303561500
S-Spec	SR3GJ; QN0A (QS)
Market	Server
Introduction	July 11, 2017 (announced); July 11, 2017 (launched)
Release Price	$417.00
Shop	Amazon
	General Specs
Family	Xeon Silver
Series	4000
Locked	Yes
Frequency	1,800 MHz
Turbo Frequency	3,000 MHz (1 core)
Clock multiplier	18
CPUID	0x50654
	Microarchitecture
ISA	x86-64 (x86)
Microarchitecture	Skylake (server)
Platform	Purley
Chipset	Lewisburg
Core Name	Skylake SP
Core Family	6
Core Stepping	U0
Process	14 nm
Technology	CMOS
Word Size	64 bit
Cores	8
Threads	16
Max Memory	768 GiB
	Multiprocessing
Max SMP	2-Way (Multiprocessor)
Interconnect	UPI
Interconnect Links	2
Interconnect Rate	9.6 GT/s
	Electrical
TDP	85 W
Tcase	0 °C – 77 °C
TDTS	0 °C – 90 °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
	Succession
	Xeon Silver 4208

Latest revision as of 12:16, 29 December 2019

Xeon Silver 4108 is a 64-bit octa-core x86 dual-socket mid-range performance server microprocessor introduced by Intel in mid-2017. The Silver 4108, 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 two Ultra Path Interconnect links. This microprocessor, which operates at 1.8 GHz with a TDP of 85 W and a turbo boost frequency of up to 3 GHz, supports up 768 GiB of hexa-channel DDR4-2400 ECC memory.

Cache[edit]

Main article: Skylake § Cache

[Edit/Modify Cache Info]

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$

512 KiB

524,288 B
0.5 MiB

L1I$	256 KiB 262,144 B 0.25 MiB	8x32 KiB	8-way set associative
L1D$	256 KiB 262,144 B 0.25 MiB	8x32 KiB	8-way set associative	write-back

L2$

8 MiB

8,192 KiB
8,388,608 B
0.00781 GiB

		8x1 MiB	16-way set associative	write-back

L3$

11 MiB

11,264 KiB
11,534,336 B
0.0107 GiB

		8x1.375 MiB	11-way set associative	write-back

Memory controller[edit]

[Edit/Modify Memory Info]

Integrated Memory Controller

Max Type	DDR4-2400
Supports ECC	Yes
Max Mem	768 GiB
Controllers	2
Channels	6
Max 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
Bandwidth	Single 17.88 GiB/s Double 35.76 GiB/s Quad 71.53 GiB/s Hexa 107.3 GiB/s

Expansions[edit]

[Edit/Modify Expansions Info]

Expansion Options

PCIe

Revision	3.0
Max Lanes	48
Configs	x16, x8, x4

Features[edit]

[Edit/Modify Supported Features]

Supported x86 Extensions & Processor Features

MMX	MMX Extension
EMMX	Extended MMX Extension
SSE	Streaming SIMD Extensions
SSE2	Streaming SIMD Extensions 2
SSE3	Streaming SIMD Extensions 3
SSSE3	Supplemental SSE3
SSE4.1	Streaming SIMD Extensions 4.1
SSE4.2	Streaming SIMD Extensions 4.2
AVX	Advanced Vector Extensions
AVX2	Advanced Vector Extensions 2
AVX-512	Advanced Vector 512-bit
AVX512F	AVX-512 Foundation
AVX512CD	AVX-512 Conflict Detection
AVX512BW	AVX-512 Byte and Word
AVX512DQ	AVX-512 Doubleword and Quadword Instructions
AVX512VL	AVX-512 Vector Length
ABM	Advanced Bit Manipulation
BMI1	Bit Manipulation Instruction Set 1
BMI2	Bit Manipulation Instruction Set 2
FMA3	3-Operand Fused-Multiply-Add
AES	AES Encryption Instructions
RdRand	Hardware RNG
ADX	Multi-Precision Add-Carry
CLMUL	Carry-less Multiplication Extension
F16C	16-bit Floating Point Conversion

x86-16	16-bit x86
x86-32	32-bit x86
x86-64	64-bit x86
Real	Real Mode
Protected	Protected Mode
SMM	System Management Mode
FPU	Integrated x87 FPU
NX	No-eXecute
HT	Hyper-Threading
TBT 2.0	Turbo Boost Technology 2.0
EIST	Enhanced SpeedStep Technology
SST	Speed Shift Technology
TXT	Trusted Execution Technology (SMX)
vPro	Intel vPro
VT-x	VT-x (Virtualization)
VT-d	VT-d (I/O MMU virtualization)
EPT	Extended Page Tables (SLAT)
TSX	Transactional Synchronization Extensions
VMD	Volume Management Device
NM	Node Manager
KPT	Key Protection Technology
PTT	Platform Trust Technology
MBE Ctrl	Mode-Based Execute Control

Frequencies[edit]

See also: Intel's CPU Frequency Behavior

[Modify Frequency Info]

Mode	Base	Turbo Frequency/Active Cores
Mode	Base	1	2	3	4	5	6	7	8
Normal	1,800 MHz	3,000 MHz	3,000 MHz	2,700 MHz	2,700 MHz	2,100 MHz	2,100 MHz	2,100 MHz	2,100 MHz
AVX2	1,400 MHz	2,900 MHz	2,900 MHz	2,300 MHz	2,300 MHz	1,800 MHz	1,800 MHz	1,800 MHz	1,800 MHz
AVX512	900 MHz	1,800 MHz	1,800 MHz	1,500 MHz	1,500 MHz	1,200 MHz	1,200 MHz	1,200 MHz	1,200 MHz

Benchmarks[edit]

[Edit Benchmarks]

Test: SPEC CPU2017
Tested: 2017-10-26 18:22:55-0400
Chips: 2, Cores: 16, Copies: 32

Vendor: HPE
System: ProLiant DL380 Gen10 (1.80 GHz, Intel Xeon Silver 4108)

SPECrate2017_int_base: 65.5

Test: SPEC CPU2017
Tested: 2017-10-25 08:47:13-0400
Chips: 2, Cores: 16, Threads: 16

Vendor: HPE
System: ProLiant DL380 Gen10 (1.80 GHz, Intel Xeon Silver 4108)

SPECspeed2017_int_base: 6.85

Test: SPEC CPU2017
Tested: 2017-10-25 12:03:49-0400
Chips: 2, Cores: 16, Threads: 16

Vendor: HPE
System: ProLiant DL380 Gen10 (1.80 GHz, Intel Xeon Silver 4108)

SPECspeed2017_fp_base: 56.3

Test: SPEC CPU2017
Tested: 2017-10-26 08:39:40-0400
Chips: 2, Cores: 16, Copies: 32

Vendor: HPE
System: ProLiant DL380 Gen10 (1.80 GHz, Intel Xeon Silver 4108)

SPECrate2017_fp_base: 77.5

@@ Line 1: / Line 1: @@
 {{intel title|Xeon Silver 4108}}
-{{mpu
+{{chip
 |name=Xeon Silver 4108
 |image=skylake sp (basic).png
@@ Line 9: / Line 9: @@
 |part number 2=CD8067303561500
 |s-spec=SR3GJ
+|s-spec qs=QN0A
 |market=Server
 |first announced=July 11, 2017
@@ Line 19: / Line 20: @@
 |turbo frequency1=3,000 MHz
 |clock multiplier=18
+|cpuid=0x50654
 |isa=x86-64
 |isa family=x86
-|microarch=Skylake
+|microarch=Skylake (server)
 |platform=Purley
 |chipset=Lewisburg
@@ Line 32: / Line 34: @@
 |core count=8
 |thread count=16
+|max memory=768 GiB
 |max cpus=2
-|max memory=768 GiB
+|smp interconnect=UPI
+|smp interconnect links=2
+|smp interconnect rate=9.6 GT/s
 |tdp=85 W
 |tcase min=0 °C
 |tcase max=77 °C
-|package module 1={{packages/intel/fclga-3647}}
+|dts min=0 °C
+|dts max=90 °C
+|package name 1=intel,fclga_3647
+|successor=Xeon Silver 4208
+|successor link=intel/xeon_silver/4208
 }}
-'''Xeon Silver 4108''' is a {{arch|64}} [[octa-core]] [[x86]] dual-socket mid-range performance server microprocessor introduced by [[Intel]] in mid-2017. The Silver 4108, which is based on the server configuration of the {{intel|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 two {{intel|Ultra Path Interconnect}} links. This microprocessor, which operates at 1.8 GHz with a TDP of 85 W and a {{intel|turbo boost}} frequency of up to 3 GHz, supports up 768 GiB of hexa-channel DDR4-2400 ECC memory.
+'''Xeon Silver 4108''' is a {{arch|64}} [[octa-core]] [[x86]] dual-socket mid-range performance server microprocessor introduced by [[Intel]] in mid-2017. The Silver 4108, 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 two {{intel|Ultra Path Interconnect}} links. This microprocessor, which operates at 1.8 GHz with a TDP of 85 W and a {{intel|turbo boost}} frequency of up to 3 GHz, supports up 768 GiB of hexa-channel DDR4-2400 ECC memory.
 == Cache ==
-{{main|intel/microarchitectures/skylake#Memory_Hierarchy|l1=Skylake § Cache}}
+{{main|intel/microarchitectures/skylake_(server)#Memory_Hierarchy|l1=Skylake § Cache}}
 {{cache size
 |l1 cache=512 KiB
@@ Line 104: / Line 113: @@
 |sse42=Yes
 |sse4a=No
+|sse_gfni=No
 |avx=Yes
+|avx_gfni=No
 |avx2=Yes
 |avx512f=Yes
@@ Line 116: / Line 127: @@
 |avx512vbmi=No
 |avx5124fmaps=No
+|avx512vnni=No
 |avx5124vnniw=No
 |avx512vpopcntdq=No
+|avx512gfni=No
+|avx512vaes=No
+|avx512vbmi2=No
+|avx512bitalg=No
+|avx512vpclmulqdq=No
 |abm=Yes
 |tbm=No
@@ Line 131: / Line 148: @@
 |clmul=Yes
 |f16c=Yes
+|bfloat16=No
 |tbt1=No
 |tbt2=Yes
 |tbmt3=No
+|tvb=No
 |bpt=No
 |eist=Yes
@@ Line 140: / Line 159: @@
 |fastmem=No
 |ivmd=Yes
+|intelnodecontroller=No
 |intelnode=Yes
 |kpt=Yes
 |ptt=Yes
+|intelrunsure=No
 |mbe=Yes
 |isrt=No
@@ Line 155: / Line 176: @@
 |vpro=Yes
 |vtx=Yes
-|vtd=No
+|vtd=Yes
 |ept=Yes
 |mpx=No
@@ Line 161: / Line 182: @@
 |securekey=No
 |osguard=No
+|intqat=No
+|dlboost=No
 |3dnow=No
 |e3dnow=No
@@ Line 174: / Line 197: @@
 |sensemi=No
 |xfr=No
+|xfr2=No
+|mxfr=No
+|amdpb=No
+|amdpb2=No
+|amdpbod=No
 }}
 == Frequencies ==
 {{see also|intel/frequency_behavior|l1=Intel's CPU Frequency Behavior}}
-{{frequency table}}
+{{frequency table
+|freq_base=1,800 MHz
+|freq_1=3,000 MHz
+|freq_2=3,000 MHz
+|freq_3=2,700 MHz
+|freq_4=2,700 MHz
+|freq_5=2,100 MHz
+|freq_6=2,100 MHz
+|freq_7=2,100 MHz
+|freq_8=2,100 MHz
+|freq_avx2_base=1,400 MHz
+|freq_avx2_1=2,900 MHz
+|freq_avx2_2=2,900 MHz
+|freq_avx2_3=2,300 MHz
+|freq_avx2_4=2,300 MHz
+|freq_avx2_5=1,800 MHz
+|freq_avx2_6=1,800 MHz
+|freq_avx2_7=1,800 MHz
+|freq_avx2_8=1,800 MHz
+|freq_avx512_base=900 MHz
+|freq_avx512_1=1,800 MHz
+|freq_avx512_2=1,800 MHz
+|freq_avx512_3=1,500 MHz
+|freq_avx512_4=1,500 MHz
+|freq_avx512_5=1,200 MHz
+|freq_avx512_6=1,200 MHz
+|freq_avx512_7=1,200 MHz
+|freq_avx512_8=1,200 MHz
+}}
+== Benchmarks ==
+{{benchmarks main
+|
+{{benchmark entry|type=spec_cpu2017|test_link=https://www.spec.org/cpu2017/results/res2017q4/cpu2017-20171031-00433.html|test_timestamp=2017-10-26 18:22:55-0400|chip_count=2|core_count=16|copies_count=32|vendor=HPE|system=ProLiant DL380 Gen10 (1.80 GHz, Intel Xeon Silver 4108)|SPECrate2017_int_base=65.5|SPECrate2017_int_peak=}}
+{{benchmark entry|type=spec_cpu2017|test_link=https://www.spec.org/cpu2017/results/res2017q4/cpu2017-20171031-00440.html|test_timestamp=2017-10-25 08:47:13-0400|chip_count=2|core_count=16|thread_count=16|vendor=HPE|system=ProLiant DL380 Gen10 (1.80 GHz, Intel Xeon Silver 4108)|SPECspeed2017_int_base=6.85|SPECspeed2017_int_peak=}}
+{{benchmark entry|type=spec_cpu2017|test_link=https://www.spec.org/cpu2017/results/res2017q4/cpu2017-20171031-00457.html|test_timestamp=2017-10-25 12:03:49-0400|chip_count=2|core_count=16|thread_count=16|vendor=HPE|system=ProLiant DL380 Gen10 (1.80 GHz, Intel Xeon Silver 4108)|SPECspeed2017_fp_base=56.3|SPECspeed2017_fp_peak=}}
+{{benchmark entry|type=spec_cpu2017|test_link=https://www.spec.org/cpu2017/results/res2017q4/cpu2017-20171031-00475.html|test_timestamp=2017-10-26 08:39:40-0400|chip_count=2|core_count=16|copies_count=32|vendor=HPE|system=ProLiant DL380 Gen10 (1.80 GHz, Intel Xeon Silver 4108)|SPECrate2017_fp_base=77.5|SPECrate2017_fp_peak=}}
+}}
+[[Category:microprocessor models by intel based on skylake low core count die]]

Has subobject "Has subobject" is a predefined property representing a container construct and is provided by Semantic MediaWiki.	Xeon Silver 4108 - Intel#io +, Xeon Silver 4108 - Intel +, Xeon Silver 4108 - Intel +, Xeon Silver 4108 - Intel + and Xeon Silver 4108 - Intel +
base frequency	1,800 MHz (1.8 GHz, 1,800,000 kHz) +
chipset	Lewisburg +
clock multiplier	18 +
core count	8 +
core family	6 +
core name	Skylake SP +
core stepping	U0 +
cpuid	0x50654 +
designer	Intel +
family	Xeon Silver +
first announced	July 11, 2017 +
first launched	July 11, 2017 +
full page name	intel/xeon silver/4108 +
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 +, Enhanced SpeedStep Technology +, Speed Shift Technology +, Trusted Execution Technology +, Intel vPro Technology +, Intel VT-x +, Intel VT-d +, Extended Page Tables + and Transactional Synchronization Extensions +
has intel enhanced speedstep technology	true +
has intel speed shift technology	true +
has intel trusted execution technology	true +
has intel turbo boost technology 2 0	true +
has intel vpro technology	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 transactional synchronization extensions	true +
has x86 advanced encryption standard instruction set extension	true +
instance of	microprocessor +
isa	x86-64 +
isa family	x86 +
l1$ size	512 KiB (524,288 B, 0.5 MiB) +
l1d$ description	8-way set associative +
l1d$ size	256 KiB (262,144 B, 0.25 MiB) +
l1i$ description	8-way set associative +
l1i$ size	256 KiB (262,144 B, 0.25 MiB) +
l2$ description	16-way set associative +
l2$ size	8 MiB (8,192 KiB, 8,388,608 B, 0.00781 GiB) +
l3$ description	11-way set associative +
l3$ size	11 MiB (11,264 KiB, 11,534,336 B, 0.0107 GiB) +
ldate	July 11, 2017 +
main image	+
manufacturer	Intel +
market segment	Server +
max case temperature	350.15 K (77 °C, 170.6 °F, 630.27 °R) +
max cpu count	2 +
max dts temperature	90 °C +
max memory	786,432 MiB (805,306,368 KiB, 824,633,720,832 B, 768 GiB, 0.75 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 +
max pcie lanes	48 +
microarchitecture	Skylake (server) +
min case temperature	273.15 K (0 °C, 32 °F, 491.67 °R) +
min dts temperature	0 °C +
model number	4108 +
name	Xeon Silver 4108 +
package	FCLGA-3647 +
part number	BX806734108 + and CD8067303561500 +
platform	Purley +
process	14 nm (0.014 μm, 1.4e-5 mm) +
release price	$ 417.00 (€ 375.30, £ 337.77, ¥ 43,088.61) +
s-spec	SR3GJ +
s-spec (qs)	QN0A +
series	4000 +
smp interconnect	UPI +
smp interconnect links	2 +
smp interconnect rate	9.6 GT/s +
smp max ways	2 +
socket	Socket P + and LGA-3647 +
supported memory type	DDR4-2400 +
tdp	85 W (85,000 mW, 0.114 hp, 0.085 kW) +
technology	CMOS +
thread count	16 +
turbo frequency (1 core)	3,000 MHz (3 GHz, 3,000,000 kHz) +
word size	64 bit (8 octets, 16 nibbles) +

WikiChip

The Fuse Coverage

Social Media

Companies

Microarchitectures

Technology Nodes

Intel

AMD

ARM

Cavium

Samsung

Intel

AMD

Ampere

Apple

Cavium

HiSilicon

MediaTek

NXP

Qualcomm

Renesas

Samsung

Latest revision as of 12:16, 29 December 2019

Contents

Cache[edit]

Memory controller[edit]

Expansions[edit]

Features[edit]

Frequencies[edit]

Benchmarks[edit]