From WikiChip
Cannon Lake - Microarchitectures - Intel
< intel‎ | microarchitectures

Edit Values
Cannon Lake µarch
General Info
Arch TypeCPU
DesignerIntel
ManufacturerIntel
IntroductionMay 15, 2018
Process10 nm
Core Configs2
Pipeline
TypeSuperscalar
OoOEYes
SpeculativeYes
Reg RenamingYes
Stages14-19
Decode5-way?
Instructions
ISAx86-64
ExtensionsMOVBE, MMX, SSE, SSE2, SSE3, SSSE3, SSE4.1, SSE4.2, POPCNT, AVX, AVX2, AES, PCLMUL, FSGSBASE, RDRND, FMA3, F16C, BMI, BMI2, VT-x, VT-d, TXT, TSX, RDSEED, ADCX, PREFETCHW, CLFLUSHOPT, XSAVE, SGX, MPX, AVX-512, AVX-512F, AVX-512CD, AVX-512BW, AVX-512DQ, AVX-512VL, AVX-512IFMA, AVX-512VBMI, SHA, UMIP
Cache
L1I Cache32 KiB/core
8-way set associative
L1D Cache32 KiB/core
8-way set associative
L2 Cache256 KiB/core
4-way set associative
L3 Cache2 MiB/core
Up to 16-way set associative
Succession
Contemporary
Coffee Lake

Cannon Lake (CNL) (formerly Skymont) is a planned microarchitecture by Intel as a successor to Kaby Lake. Cannon Lake is expected to be fabricated using a 10 nm process and is set to be introduced in the second half of 2018. Cannon Lake is the "Process" microarchitecture as part of Intel's PAO model.

For mobile, Cannon Lake is expected to be branded as 8th Generation Intel Core i3, Core i5. and Core i7 processors.

Codenames

Core Abbrev Description Graphics Target
Cannon Lake U CNL-U Ultra-low Power GT2/GT3 Light notebooks, portable All-in-Ones (AiOs), Minis, and conference room

Release Dates

Initial Cannon Lake models were introduced in May 2018 with additional models planned throughout the year.

Process Technology

Cannon Lake is manufactured on Intel's 10 nm process (P1274). Intel's 10 nm process is among the first high-volume manufacturing processes to employ Self-Aligned Quad Patterning (SAQP) (goes under the "Hyper-Scaling" marketing name). Intel's 10nm features a 0.0367 µm² SRAM bit cell.

Scaling:

Broadwell Cannon
Lake
Δ intel 10nm fin.png
14 nm 10 nm
Fin Pitch  42 nm  34 nm 0.81x
Fin Width​   8 nm   7 nm 0.88x
Fin Height​  42 nm  53 nm 1.24x
Gate Pitch  70 nm  54 nm 0.77x
Interconnect Pitch  52 nm  36 nm 0.69x
Cell Height 399 nm 272 nm 0.68x

Compiler support

Support for Cannon Lake was added in GCC 8.1 and LLVM 6.0.

Compiler Arch-Specific Arch-Favorable
ICC -march=cannonlake -mtune=cannonlake
GCC -march=cannonlake -mtune=cannonlake
LLVM -march=cannonlake -mtune=cannonlake
Visual Studio ? ?

CPUID

Core Extended
Family
Family Extended
Model
Model
U 0 0x6 0x6 0x6
Family 6 Model 102

Architecture

Key changes from Skylake

  • Mobile Processors
    • LPDDR4/LPDDR4X memory support (from LPDDR3)
      • Rates up to 2400 MT/s
  • Gen9.5Gen10 graphics
  • Gen10 GPUs
    • HD Graphics 6xx (GT1) UHD Graphics 7xx (GT1) (24 Execution Units, 2x EUs from Skylake)
    • HD Graphics 6xx (GT2) UHD Graphics 7xx (GT2) (40 Execution Units, 1.7x EUs from Skylake)
  • New Integration
    • New Gaussian Neural Accelerator 1.0 (Unclear to what extent)

New instructions

Cannon Lake introduced a number of new instructions. See Palm Cove § New Instructions for details.

Block Diagram

Entire SoC Overview

800px

Individual Core

See Palm Cove § Block Diagram.

Gen11 Graphics

See Gen10 Graphics § Block Diagram.

Die

Dual-core

All Cannon Lake Chips

 List of Cannon Lake-based Processors
ModelPriceLaunchedCoresThreadsTDPFrequencyTurbo
i3-8121U15 May 20182415 W
15,000 mW
0.0201 hp
0.015 kW
2.2 GHz
2,200 MHz
2,200,000 kHz
3.2 GHz
3,200 MHz
3,200,000 kHz
M3-8114Y241.5 GHz
1,500 MHz
1,500,000 kHz
Count: 2

References

  • Some information was obtained directly from Intel.
  • Mark Bohr, Intel. Intel Technology and Manufacturing Day. Mar 28, 2017.

See also