From WikiChip
Difference between revisions of "amd/microarchitectures/navi"
< amd‎ | microarchitectures

(→‎Generation)
 
(20 intermediate revisions by 10 users not shown)
Line 1: Line 1:
−
{{amd title|GCN 6th gen|arch}}
+
{{amd title|Navi|arch}}
 
{{microarchitecture
 
{{microarchitecture
−
| atype           = GPU
+
|atype=GPU
−
| name             = GCN 6th gen
+
|name=Navi
−
| designer         = AMD
+
|designer=AMD
−
| manufacturer     = GlobalFoundries
+
|manufacturer=TSMC
−
| manufacturer 2  =  
+
|introduction=2018
−
| introduction     = 2018
+
|release=July 7, 2019
−
| phase-out        =  
+
|process=7 nm
−
| process         = 7 nm
+
|predecessor=Vega
−
 
+
|predecessor link=amd/microarchitectures/vega
−
| succession      = no
+
|successor=Navi 2x
−
| predecessor     = graphics core next 5th gen
+
|successor link=amd/microarchitectures/navi 2x
−
| predecessor link = amd/microarchitectures/graphics core next 5th gen
+
|succession=yes
−
| successor       =  
 
−
| successor link   =  
 
 
}}
 
}}
−
'''Graphics core next 6th gen''' (also known as '''Navi''') is a planned [[microarchitecture]] being developed by [[AMD]] as a successor to {{\\|graphics core next 5th gen(Vega)}}.  
+
'''Navi''' is the successor to {{\\|Vega}}, a [[7 nm]] high-performance graphics processing unit [[microarchitecture]] for the gaming market.
  
 
== Architecture ==
 
== Architecture ==
−
[[File:amd gpu roadmap.png|400px|right]]
+
[[File:amd gpu roadmap.png|400px|left]]
−
Nothing is currently known about the architectural improvements that is being done to Zen 2.
 
  
−
=== Key changes from {{\\|graphics core next 5th gen(Vega)}} ===
+
=== Key changes from {{\\|Vega}} ===
 
* [[7 nm process]] (from [[14 nm]])
 
* [[7 nm process]] (from [[14 nm]])
 +
* Architecture
 +
** {{amd|RDNA}} (from {{amd|GCN}})
 +
 +
:;Models
 +
* Navi • Radeon RX 5000 series
 +
* Navi 2x • Radeon RX 6000 series
 +
* Navi 3x • Radeon RX 7000 series
 +
 +
== Generation ==
 +
:;[[AMD]] Navi II IGP (7)
 +
 +
{| class="wikitable" cellpadding="3px" style="border: 1px solid black; border-spacing: 0px; width: 100%; text-align:center;"
 +
|-
 +
! Name !! Family !! Bus !! Memory !! GPU Clock !! Memory Clock !! Cores / TMUs / ROPs !! Release
 +
|-
 +
! Radeon 610M
 +
| Mendocino || PCIe 4.0 x8 || System Shared / DDR5 || 1900 MHz || System Shared || 128 / 8 / 4 || Sep 20, 2022
 +
|-
 +
! Radeon 610M
 +
| Dragon Range || PCIe 4.0 x8 || System Shared / GDDR6 || 2200 MHz || System Shared || 128 / 8 / 4 || Jan 3, 2023
 +
|-
 +
! Radeon 660M
 +
| Rembrandt || PCIe 4.0 x8 || System Shared / DDR5 || 1900 MHz || System Shared || 384 / 24 / 16 || Jan 4, 2022
 +
|-
 +
! Radeon 660M
 +
| Rembrandt+ || PCIe 4.0 x8 || System Shared / DDR5 || 1900 MHz || System Shared || 384 / 24 / 16 || Jan 3, 2023
 +
|-
 +
! Radeon 680M
 +
| Rembrandt || PCIe 4.0 x8 || System Shared / DDR5 || 2200 MHz || System Shared || 768 / 48 / 32 || Jan 4, 2022
 +
|-
 +
! Radeon 680M
 +
| Rembrandt+ || PCIe 4.0 x8 || System Shared / DDR5 || 2200 MHz || System Shared || 768 / 48 / 32 || Jan 3, 2023
 +
|-
 +
! Radeon Graphics 128SP
 +
| Raphael || PCIe 4.0 x8 || System Shared / GDDR6 || 2200 MHz || System Shared || 128 / 8 / 8 || Sep 27, 2022
 +
|}
 +
 +
:;AMD Navi III IGP (12)
 +
 +
{| class="wikitable" cellpadding="3px" style="border: 1px solid black; border-spacing: 0px; width: 100%; text-align:center;"
 +
|-
 +
! Name !! Family !! Bus !! Memory !! GPU Clock !! Memory Clock !! Cores / TMUs / ROPs !! Release
 +
|-
 +
! Radeon 740M
 +
| Phoenix || PCIe 4.0 x8 || System Shared / DDR5 || 2500 MHz || System Shared || 256 / 16 / 8 || Jan 4th, 2023
 +
|-
 +
! Radeon 740M
 +
| Hawk Point || PCIe 4.0 x8 || System Shared / DDR5 || 2800 MHz || System Shared || 256 / 16 / 8 || Dec 6, 2023
 +
|-
 +
! Radeon 740M
 +
| Phoenix2 || PCIe 4.0 x8 || System Shared / DDR5 || 2800 MHz || System Shared || 256 / 16 / 8 || Jan 31, 2024
 +
|-
 +
! Radeon 760M
 +
| Phoenix || PCIe 4.0 x8 || System Shared / DDR5 || 2600 MHz || System Shared || 512 / 32 / 16 || Jan 4, 2023
 +
|-
 +
! Radeon 760M
 +
| Hawk Point || PCIe 4.0 x8 || System Shared / DDR5 || 2600 MHz || System Shared || 512 / 32 / 16 || Dec 6, 2023
 +
|-
 +
! Radeon 760M
 +
| Phoenix || PCIe 4.0 x8 || System Shared / DDR5 || 2600 MHz || System Shared || 512 / 32 / 16 || Jan 31, 2024
 +
|-
 +
! Radeon 780M
 +
| Phoenix || PCIe 4.0 x8 || System Shared / DDR5 || 2700 MHz || System Shared || 768 / 48 / 32 || Jan 4, 2023
 +
|-
 +
! Radeon 780M
 +
| Hawk Point || PCIe 4.0 x8 || System Shared / DDR5 || 2700 MHz || System Shared || 768 / 48 / 32 || Dec 6, 2023
 +
|-
 +
! Radeon 780M
 +
| Phoenix || PCIe 4.0 x8 || System Shared / DDR5 || 2900 MHz || System Shared || 768 / 48 / 32 || Jan 31, 2024
 +
|-
 +
! Radeon 840M
 +
| Krackan Point || PCIe 4.0 x8 || System Shared / DDR5 || 2900 MHz || System Shared || 256 / 16 / 8 || Mar 15, 2025
 +
|-
 +
! Radeon 860M
 +
| Krackan Point || PCIe 4.0 x8 || System Shared / DDR5 || 3000 MHz || System Shared || 512 / 32 / 16 || Mar 15, 2025
 +
|-
 +
! Radeon 880M
 +
| Strix Point || PCIe 4.0 x8 || System Shared / DDR5 || 2900 MHz || System Shared || 768 / 48 / 16 || Jul 15, 2024
 +
|-
 +
! Radeon 890M
 +
| Strix Point || PCIe 4.0 x8 || System Shared / DDR5 || 2900 MHz || System Shared || 1024 / 64 / 32 || Jul 15, 2024
 +
|}
 +
 +
=== Comparison of RDNA chips ===
 +
 +
{| class="wikitable" cellpadding="3px" style="border: 1px solid black; border-spacing: 0px; width: 100%; text-align:center;"
 +
|+RDNA integrated GPU chips
 +
|-
 +
! style="min-width: 10em;" | [[Microarchitecture]]
 +
! colspan="5" | RDNA 2 (Navi II)
 +
! colspan="2" | RDNA 3 (Navi III)
 +
! colspan="3" | RDNA 3.5 (Navi III)
 +
|-
 +
! Introduced
 +
| Radeon<br>660M<hr>680M
 +
| Radeon<br>Graphics<br>128SP
 +
| Radeon<br>610M
 +
| Radeon<br>660M<hr>680M
 +
| Radeon<br>610M
 +
| 740M<hr>760M<hr>780M
 +
| 740M<hr>760M<hr>780M
 +
| Radeon<br>880M<hr>890M <ref>{{cite book |title=AMD Details the Radeon 890M RDNA 3.5 iGPU of "Strix Point" a bit More |url=https://www.techpowerup.com/324874/amd-details-the-radeon-890m-rdna-3-5-igpu-of-strix-point-a-bit-more |access-date=September 7, 2024 |website=TechPowerUp}}</ref>
 +
| 8040S<hr>8050S<hr>8060S
 +
| Radeon<br>840M<hr>860M
 +
|-
 +
! Code name
 +
| Rembrandt
 +
| Raphael
 +
| Mendocino
 +
| Rembrandt-R
 +
| Dragon Range
 +
| Phoenix
 +
| Hawk Point
 +
| ''Strix Point'' <ref>{{cite book |title=AMD Strix Point GPU Specs |url=https://www.techpowerup.com/gpu-specs/amd-strix-point.g1079 |access-date=September 7, 2024 |website=TechPowerUp}}</ref>
 +
| ''Strix Halo'' <ref>{{cite book |title=AMD Strix Halo GPU Specs |url=https://www.techpowerup.com/gpu-specs/amd-strix-halo.g1096 |access-date=2025-10-09 |website=TechPowerUp}}</ref>
 +
|''Krackan Point'' <ref>{{cite book |title=AMD Krackan Point GPU Specs |url=https://www.techpowerup.com/gpu-specs/amd-krackan-point.g1092 |access-date=2025-10-09 |website=TechPowerUp}}</ref>
 +
|-
 +
! Mobile APU
 +
| [[Ryzen]] <br>6000
 +
| [[Ryzen]] <br>7000
 +
| [[Ryzen]] <br>7020
 +
| [[Ryzen]] <br>7035
 +
| [[Ryzen]] <br>7045
 +
| [[Ryzen]] <br>7040 (Z1)
 +
| [[Ryzen]] <br>8040
 +
| [[Ryzen]]
 +
| [[Ryzen]]
 +
| [[Ryzen]]
 +
|-
 +
! LLVM target <ref>{{cite book |title=User Guide for AMD GPU Backend — LLVM 22.0.0 git Documentation |url=https://llvm.org/docs/AMDGPUUsage.html |website=llvm.org}}</ref> <ref>{{cite book |title=Accelerator and GPU hardware specifications — ROCm Documentation |url=https://rocm.docs.amd.com/en/latest/reference/gpu-arch-specs.html |website=rocm.docs.amd.com}}</ref>
 +
| gfx1035
 +
| gfx1036
 +
| gfx1037
 +
| gfx1035
 +
| gfx1037
 +
| colspan="2" | gfx1103
 +
| gfx1150 (1)
 +
| gfx1151
 +
| gfx1152
 +
|-
 +
! Fab process
 +
| colspan="5" | [[TSMC]] [[7 nm process|N6]]
 +
| colspan="2" | [[TSMC]] [[5 nm process|N4]]
 +
| colspan="3" | [[TSMC]] [[5 nm process|N4P]]
 +
|-
 +
! Package
 +
| colspan="5" | Monolithic
 +
| colspan="2" |
 +
| Monolithic
 +
| Semi-MCM
 +
| Monolithic
 +
|-
 +
! Die&nbsp;size (mm<sup>2</sup>)
 +
| || || || ||
 +
| colspan="2" | 178
 +
| 232 || 232 / 308 || TBA
 +
|-
 +
! Workgroup processors <br>(WGP)
 +
| || ||
 +
| || || ||
 +
| 8 || 20 || 4
 +
|-
 +
! Compute units (CU)
 +
| || ||
 +
| ||
 +
| 4 (Z1)<hr>8<hr>12 (Z1E) || 4<hr>8<hr>12
 +
| 12<hr>16 || 16<hr>32<hr>40 || 4<hr>8
 +
|-
 +
! Stream processors <br>(Cores)
 +
| 384<hr>768 || 128 || 128
 +
| 384<hr>768 || 128
 +
| 256<hr>512<hr>768 || 256<hr>512<hr>768
 +
| 768<hr>1024 || 1024<hr>2048<hr>2560 || 256<hr>512
 +
|-
 +
! Texture mapping units <br>(TMU)
 +
| 24<hr>48 || 8 || 8
 +
| 24<hr>48 || 8
 +
| 16<hr>32<hr>48 || 16<hr>32<hr>48
 +
| 48<hr>64 || 64<hr>128<hr>160 || 16<hr>32
 +
|-
 +
! Render output units <br>(ROP)
 +
| 16<hr>32 || 8 || 4
 +
| 16<hr>32 || 4
 +
| 8<hr>16<hr>32 || 8<hr>16<hr>32
 +
| 24<hr>32 || 32<hr>64<hr>80 || 8<hr>16
 +
|-
 +
! RT accelerators
 +
| || ||
 +
| ||
 +
| 4 (Z1)<hr>8<hr>12 (Z1E) || 4<hr>8<hr>12
 +
| 12<hr>16 || 16<hr>32<hr>40 || 4<hr>8
 +
|-
 +
! [[AI accelerator]]s
 +
| colspan="5" |
 +
| ||
 +
| 32 || 80 || 16
 +
|-
 +
! L0&nbsp;cache (KB)
 +
| colspan="5" | 32 KB per WGP (Workgroup processor)
 +
| colspan="2" | 64 KB per WGP
 +
| colspan="3" | 64 KB per WGP
 +
|-
 +
! L1&nbsp;cache (KB)
 +
| colspan="5" | 128 KB per SA (Shader array)
 +
| colspan="2" | 256 KB per SA
 +
| colspan="3" | 256 KB per SA
 +
|-
 +
! L2&nbsp;cache (MB)
 +
| || ||
 +
| || || 2 || 2
 +
| 2 || 8 || 2
 +
|-
 +
! L3&nbsp;cache (MB)
 +
| || ||
 +
| || || 0 / 16 (Z1)|| 0
 +
| 0 || 64 || 0
 +
|-
 +
! Memory type
 +
| DDR5 /<br>LPDDR5
 +
| GDDR6
 +
| LPDDR5
 +
| DDR5 /<br>LPDDR5
 +
| GDDR6
 +
| colspan="2" | DDR5 / LPDDR5(X)
 +
| colspan="3" | DDR5 / LPDDR5(X)
 +
|-
 +
! Memory bus (bits)
 +
| colspan="3" | 128
 +
| colspan="2" | 128
 +
| colspan="2" | 128
 +
| 128 || 128 / 256 || 128
 +
|-
 +
! Display Core Next
 +
| colspan="2" | || || ||
 +
| colspan="2" |
 +
| 3.1.4 || 3.5.0 || 3.5.0
 +
|-
 +
! Video Core Next
 +
| colspan="2" | || || ||
 +
| colspan="2" |
 +
| 4.0.2 || 4.0.5 || 4.0.5
 +
|-
 +
! Launch
 +
| January <br>2022
 +
| colspan="2" | September <br>2022
 +
| colspan="2" | January <br>2023
 +
| January <br>2023 || December <br>2023
 +
| July <br>2024 || January <br>2025 || March <br>2025
 +
|}
  
 
== References ==
 
== References ==
 
* AMD 2017 Financial Analyst Day, May 16, 2017
 
* AMD 2017 Financial Analyst Day, May 16, 2017
  
−
== See Also ==
+
== See also ==
 
* [[list of microarchitectures]]
 
* [[list of microarchitectures]]
 +
* [[AMD]] • {{\\|Vega}}

Latest revision as of 11:24, 6 November 2025

Edit Values
Navi µarch
General Info
Arch TypeGPU
DesignerAMD
ManufacturerTSMC
Introduction2018
Process7 nm
Succession

Navi is the successor to Vega, a 7 nm high-performance graphics processing unit microarchitecture for the gaming market.

Architecture[edit]

amd gpu roadmap.png

Key changes from Vega[edit]

Models
  • Navi • Radeon RX 5000 series
  • Navi 2x • Radeon RX 6000 series
  • Navi 3x • Radeon RX 7000 series

Generation[edit]

AMD Navi II IGP (7)
Name Family Bus Memory GPU Clock Memory Clock Cores / TMUs / ROPs Release
Radeon 610M Mendocino PCIe 4.0 x8 System Shared / DDR5 1900 MHz System Shared 128 / 8 / 4 Sep 20, 2022
Radeon 610M Dragon Range PCIe 4.0 x8 System Shared / GDDR6 2200 MHz System Shared 128 / 8 / 4 Jan 3, 2023
Radeon 660M Rembrandt PCIe 4.0 x8 System Shared / DDR5 1900 MHz System Shared 384 / 24 / 16 Jan 4, 2022
Radeon 660M Rembrandt+ PCIe 4.0 x8 System Shared / DDR5 1900 MHz System Shared 384 / 24 / 16 Jan 3, 2023
Radeon 680M Rembrandt PCIe 4.0 x8 System Shared / DDR5 2200 MHz System Shared 768 / 48 / 32 Jan 4, 2022
Radeon 680M Rembrandt+ PCIe 4.0 x8 System Shared / DDR5 2200 MHz System Shared 768 / 48 / 32 Jan 3, 2023
Radeon Graphics 128SP Raphael PCIe 4.0 x8 System Shared / GDDR6 2200 MHz System Shared 128 / 8 / 8 Sep 27, 2022
AMD Navi III IGP (12)
Name Family Bus Memory GPU Clock Memory Clock Cores / TMUs / ROPs Release
Radeon 740M Phoenix PCIe 4.0 x8 System Shared / DDR5 2500 MHz System Shared 256 / 16 / 8 Jan 4th, 2023
Radeon 740M Hawk Point PCIe 4.0 x8 System Shared / DDR5 2800 MHz System Shared 256 / 16 / 8 Dec 6, 2023
Radeon 740M Phoenix2 PCIe 4.0 x8 System Shared / DDR5 2800 MHz System Shared 256 / 16 / 8 Jan 31, 2024
Radeon 760M Phoenix PCIe 4.0 x8 System Shared / DDR5 2600 MHz System Shared 512 / 32 / 16 Jan 4, 2023
Radeon 760M Hawk Point PCIe 4.0 x8 System Shared / DDR5 2600 MHz System Shared 512 / 32 / 16 Dec 6, 2023
Radeon 760M Phoenix PCIe 4.0 x8 System Shared / DDR5 2600 MHz System Shared 512 / 32 / 16 Jan 31, 2024
Radeon 780M Phoenix PCIe 4.0 x8 System Shared / DDR5 2700 MHz System Shared 768 / 48 / 32 Jan 4, 2023
Radeon 780M Hawk Point PCIe 4.0 x8 System Shared / DDR5 2700 MHz System Shared 768 / 48 / 32 Dec 6, 2023
Radeon 780M Phoenix PCIe 4.0 x8 System Shared / DDR5 2900 MHz System Shared 768 / 48 / 32 Jan 31, 2024
Radeon 840M Krackan Point PCIe 4.0 x8 System Shared / DDR5 2900 MHz System Shared 256 / 16 / 8 Mar 15, 2025
Radeon 860M Krackan Point PCIe 4.0 x8 System Shared / DDR5 3000 MHz System Shared 512 / 32 / 16 Mar 15, 2025
Radeon 880M Strix Point PCIe 4.0 x8 System Shared / DDR5 2900 MHz System Shared 768 / 48 / 16 Jul 15, 2024
Radeon 890M Strix Point PCIe 4.0 x8 System Shared / DDR5 2900 MHz System Shared 1024 / 64 / 32 Jul 15, 2024

Comparison of RDNA chips[edit]

RDNA integrated GPU chips
Microarchitecture RDNA 2 (Navi II) RDNA 3 (Navi III) RDNA 3.5 (Navi III)
Introduced Radeon
660M
680M 		Radeon
Graphics
128SP 		Radeon
610M 		Radeon
660M
680M 		Radeon
610M 		740M
760M
780M 		740M
760M
780M 		Radeon
880M
890M [1] 		8040S
8050S
8060S 		Radeon
840M
860M
Code name Rembrandt Raphael Mendocino Rembrandt-R Dragon Range Phoenix Hawk Point Strix Point [2] Strix Halo [3] Krackan Point [4]
Mobile APU Ryzen
6000 		Ryzen
7000 		Ryzen
7020 		Ryzen
7035 		Ryzen
7045 		Ryzen
7040 (Z1) 		Ryzen
8040 		Ryzen Ryzen Ryzen
LLVM target [5] [6] gfx1035 gfx1036 gfx1037 gfx1035 gfx1037 gfx1103 gfx1150 (1) gfx1151 gfx1152
Fab process TSMC N6 TSMC N4 TSMC N4P
Package Monolithic Monolithic Semi-MCM Monolithic
Die size (mm2) 178 232 232 / 308 TBA
Workgroup processors
(WGP) 		8 20 4
Compute units (CU) 4 (Z1)
8
12 (Z1E) 		4
8
12 		12
16 		16
32
40 		4
8
Stream processors
(Cores) 		384
768 		128 128 384
768 		128 256
512
768 		256
512
768 		768
1024 		1024
2048
2560 		256
512
Texture mapping units
(TMU) 		24
48 		8 8 24
48 		8 16
32
48 		16
32
48 		48
64 		64
128
160 		16
32
Render output units
(ROP) 		16
32 		8 4 16
32 		4 8
16
32 		8
16
32 		24
32 		32
64
80 		8
16
RT accelerators 4 (Z1)
8
12 (Z1E) 		4
8
12 		12
16 		16
32
40 		4
8
AI accelerators 32 80 16
L0 cache (KB) 32 KB per WGP (Workgroup processor) 64 KB per WGP 64 KB per WGP
L1 cache (KB) 128 KB per SA (Shader array) 256 KB per SA 256 KB per SA
L2 cache (MB) 2 2 2 8 2
L3 cache (MB) 0 / 16 (Z1) 0 0 64 0
Memory type DDR5 /
LPDDR5 		GDDR6 LPDDR5 DDR5 /
LPDDR5 		GDDR6 DDR5 / LPDDR5(X) DDR5 / LPDDR5(X)
Memory bus (bits) 128 128 128 128 128 / 256 128
Display Core Next 3.1.4 3.5.0 3.5.0
Video Core Next 4.0.2 4.0.5 4.0.5
Launch January
2022 		September
2022 		January
2023 		January
2023 		December
2023 		July
2024 		January
2025 		March
2025

References[edit]

  • AMD 2017 Financial Analyst Day, May 16, 2017

See also[edit]

  • ↑ AMD Details the Radeon 890M RDNA 3.5 iGPU of "Strix Point" a bit More.
  • ↑ AMD Strix Point GPU Specs.
  • ↑ AMD Strix Halo GPU Specs.
  • ↑ AMD Krackan Point GPU Specs.
  • ↑ User Guide for AMD GPU Backend — LLVM 22.0.0 git Documentation.
  • ↑ Accelerator and GPU hardware specifications — ROCm Documentation.
    • Retrieved from "https://en.wikichip.org/w/index.php?title=amd/microarchitectures/navi&oldid=103929"
    Facts about "Navi - Microarchitectures - AMD"
    RDF feed
    codenameNavi +
    designerAMD +
    first launched2018 +
    full page nameamd/microarchitectures/navi +
    instance ofmicroarchitecture +
    manufacturerTSMC +
    microarchitecture typeGPU +
    nameNavi +
    process7 nm (0.007 μm, 7.0e-6 mm) +