From WikiChip
Difference between revisions of "intel/cores/kaby lake g"
< intel

(→‎Kaby Lake G Processors: added vpro to the table)
(→‎Kaby Lake G Processors: missing TDP)
Line 87: Line 87:
 
-->
 
-->
 
{{comp table start}}
 
{{comp table start}}
−
<table class="comptable sortable tc4 tc5 tc12 tc13">
+
<table class="comptable sortable tc4 tc5 tc13 tc14">
−
{{comp table header|main|12:List of Kaby Lake G-based Processors}}
+
{{comp table header|main|13:List of Kaby Lake G-based Processors}}
−
{{comp table header|main|7:Main processor|3:Graphics Processors|2:Features}}
+
{{comp table header|main|8:Main processor|3:Graphics Processors|2:Features}}
−
{{comp table header|cols|Launched|Family|C|T|L3$|%Frequency|%Turbo|GPU|Base|Burst|vPro|Locked}}
+
{{comp table header|cols|Launched|Family|C|T|L3$|TDP|%Frequency|%Turbo|GPU|Base|Burst|vPro|Locked}}
 
{{#ask: [[Category:microprocessor models by intel]] [[instance of::microprocessor]] [[core name::Kaby Lake G]]
 
{{#ask: [[Category:microprocessor models by intel]] [[instance of::microprocessor]] [[core name::Kaby Lake G]]
 
  |?full page name
 
  |?full page name
Line 99: Line 99:
 
  |?thread count
 
  |?thread count
 
  |?l3$ size
 
  |?l3$ size
 +
|?tdp
 
  |?base frequency#GHz
 
  |?base frequency#GHz
 
  |?turbo frequency (1 core)#GHz
 
  |?turbo frequency (1 core)#GHz
Line 108: Line 109:
 
  |format=template
 
  |format=template
 
  |template=proc table 3
 
  |template=proc table 3
−
  |userparam=14:13
+
  |userparam=15:14
 
  |mainlabel=-
 
  |mainlabel=-
 
  |valuesep=,
 
  |valuesep=,

Revision as of 10:44, 7 January 2018

Edit Values
Kaby Lake G
kaby lake g (front).png
Package front
General Info
DesignerIntel, AMD
ManufacturerIntel, GlobalFoundries
IntroductionNovember 6, 2017 (announced)
January 7, 2018 (launched)
Microarchitecture
ISAx86-64 (x86)
MicroarchitectureKaby Lake
Word Size
8 octets
16 nibbles
64 bit
Process14 nm
0.014 μm
1.4e-5 mm
TechnologyCMOS

Kaby Lake G (KBL-G) is the name of the core for Intel's high-performance line of mobile processors based on the Kaby Lake microarchitecture and incorporate a discrete AMD Vega graphics processor. These chips are targeted towards ultimate mobile gaming experience. Kaby Lake G processors are fabricated on Intel's enhanced 14nm+ process and for graphics, GlobalFoundries 14 nm process.


Symbol version future.svg Preliminary Data! Information presented in this article deal with future products, data, features, and specifications that have yet to be finalized, announced, or released. Information may be incomplete and can change by final release.


Overview

8th gen core i7 with radeon logo (2018).png
8th gen core i5 with radeon logo (2018).png

Kaby Lake G based processors are a 2-chip solution - the microprocessor and the chipset. Those parts are BGA and are soldered onto the motherboard. The microprocessor is connected to the chipset via 4 of the chip's 20 PCIe lanes using Intel's proprietary Direct Media Interface 3.0 (DMI 3.0), allowing for 8 GT/s transfer rate per lane.

Graphics

Those processors are unique in the fact that this is the first time Intel has integrated a discrete graphics processor into the same package as the microprocessor. This is also the first time they are using a competitor graphics processor. Those parts incorporate an AMD GPU based on the Vega microarchitecture and incorporate their own 4 GiB of high-bandwidth memory 2 (HBM2). The HBM solution is connected to the graphics processor using Intel's EMIB, a high-speed in-package interconnect solution.

The CPU itself is connected to the GPU using 8 of the other PCIe lanes, leaving the 8 remaining lanes for other peripherals to communicate with the CPU directly.


kaby lake g with amd radeon package.png


Common Features

All Kaby Lake G processors have the following:

  • Dual-channel Memory
    • Up to DDR3L-1600, DDR4-2400
    • Up to 64 GiB
  • 8x PCIe
    • 20x in total, 4 of the 20 are used by the bus and 8 for the GPU as described above
  • quad-core with Hyper-Threading (8 threads)
  • Everything up to AVX2 (SMM, FPU, NX, MMX, SSE, SSE2, SSE3, SSSE3, SSE4.1, SSE4.2, AES, AVX, and AVX2)
  • BGA package

Graphics

Graphics Subsystem

Those processors have superior graphics capabilities as well as 4 GiB of HBM 2 cache.

  • HBM 2 (Intel calls "High Bandwidth Cache" or "HBC")
    • 4 GiB
    • 1,024 bit
      • @ 800 MHz (204.8 GB/s peak bandwidth)
      • @ 700 MHz (179.2 GB/s peak bandwidth)
  • Graphics
    • 9 Display outputs available
    • Integrated HD Graphics 630 (Gen9.5 GT2)
      • 3 Displays
      • Base frequency of 350 MHz
      • Burst frequency of 1.1 GHz
    • Discrete Vega-based GPUs
      • Custom Radeon RX Vega M Graphics
        • 6 Displays
        • Radeon RX Vega M GH
          • 24 Compute Units
          • 1,536 Stream processors, 64 pix/clk (ROPs), 96 texture units
          • 3.7 TFLOPS peak performance
        • Radeon RX Vega M GL
          • 20 Compute Units
          • 1,280 Stream processors, 32 pix/clk (ROPs), 80 texture units
          • 2.6 TFLOPS peak performance

Kaby Lake G Processors

 List of Kaby Lake G-based Processors
 Main processorGraphics ProcessorsFeatures
ModelLaunchedFamilyCTL3$TDPFrequencyTurboGPUBaseBurstvProLocked
i5-8305G7 January 2018Core i5486 MiB
6,144 KiB
6,291,456 B
0.00586 GiB
65 W
65,000 mW
0.0872 hp
0.065 kW
2.8 GHz
2,800 MHz
2,800,000 kHz
3.8 GHz
3,800 MHz
3,800,000 kHz
HD Graphics 630, Radeon RX Vega M GL350 MHz
0.35 GHz
350,000 KHz
, 931 MHz
0.931 GHz
931,000 KHz
1,100 MHz
1.1 GHz
1,100,000 KHz
, 1,011 MHz
1.011 GHz
1,011,000 KHz
✘✔
i7-8705G7 January 2018Core i7488 MiB
8,192 KiB
8,388,608 B
0.00781 GiB
65 W
65,000 mW
0.0872 hp
0.065 kW
3.1 GHz
3,100 MHz
3,100,000 kHz
4.1 GHz
4,100 MHz
4,100,000 kHz
HD Graphics 630, Radeon RX Vega M GL350 MHz
0.35 GHz
350,000 KHz
, 931 MHz
0.931 GHz
931,000 KHz
1,100 MHz
1.1 GHz
1,100,000 KHz
, 1,011 MHz
1.011 GHz
1,011,000 KHz
✘✔
i7-8706G7 January 2018Core i7488 MiB
8,192 KiB
8,388,608 B
0.00781 GiB
65 W
65,000 mW
0.0872 hp
0.065 kW
3.1 GHz
3,100 MHz
3,100,000 kHz
4.1 GHz
4,100 MHz
4,100,000 kHz
HD Graphics 630, Radeon RX Vega M GL350 MHz
0.35 GHz
350,000 KHz
, 931 MHz
0.931 GHz
931,000 KHz
1,100 MHz
1.1 GHz
1,100,000 KHz
, 1,011 MHz
1.011 GHz
1,011,000 KHz
✔✔
i7-8809G7 January 2018Core i7488 MiB
8,192 KiB
8,388,608 B
0.00781 GiB
100 W
100,000 mW
0.134 hp
0.1 kW
3.1 GHz
3,100 MHz
3,100,000 kHz
4.2 GHz
4,200 MHz
4,200,000 kHz
HD Graphics 630, Radeon RX Vega M GH350 MHz
0.35 GHz
350,000 KHz
, 1,063 MHz
1.063 GHz
1,063,000 KHz
1,100 MHz
1.1 GHz
1,100,000 KHz
, 1,190 MHz
1.19 GHz
1,190,000 KHz
✘✘
Count: 4

See also

arrow up 1.svgPower/Performance

Retrieved from "https://en.wikichip.org/w/index.php?title=intel/cores/kaby_lake_g&oldid=72167"
Facts about "Kaby Lake G - Cores - Intel"
RDF feed
designerIntel + and AMD +
first announcedNovember 6, 2017 +
first launchedJanuary 7, 2018 +
instance ofcore +
isax86-64 +
isa familyx86 +
main imageFile:kaby lake g (front).png +
main image captionPackage front +
manufacturerIntel + and GlobalFoundries +
microarchitectureKaby Lake +
nameKaby Lake G +
process14 nm (0.014 μm, 1.4e-5 mm) +
technologyCMOS +
word size64 bit (8 octets, 16 nibbles) +