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

(→‎Comparison of RDNA chips)
(→‎Family)
 
(4 intermediate revisions by 2 users not shown)
Line 28: Line 28:
 
* Navi 2x • Radeon RX 6000 series
 
* Navi 2x • Radeon RX 6000 series
 
* Navi 3x • Radeon RX 7000 series
 
* Navi 3x • Radeon RX 7000 series
 +
 +
== Family ==
 +
{| class="wikitable" cellpadding="3px" style="border: 1px solid black; border-spacing: 0px; width: 100%; text-align:center;"
 +
|-
 +
! Family !! Chipset name !! [[Microarchitecture]] !! ISA !! Product name
 +
|-
 +
! {{\\|Southern Islands}}
 +
| Cape Verde, Hainan, Oland, Pitcairn, Tahiti || GCN1.0+ || DCE 6.x || HD7750 - HD7970, R9 270, R9 280, R9 370X, R7 240, R7 250
 +
|-
 +
! {{\\|Sea Islands}}
 +
| Bonaire, Hawaii, Kabini, Kaveri, Mullins || GCN2.x || DCE 8.x || HD7790, R7 260, R9 290, R7 360, R9 390
 +
|-
 +
! {{\\|Volcanic Islands}}
 +
| Fiji, Iceland, Stoney, Tonga, Topaz, Wani || GCN3.x || DCE 10/11.x || R9 285, R9 380/380X, R9 Fury, R9 Nano, R9 Fury X, Pro Duo
 +
|-
 +
! {{\\|Arctic Islands}}
 +
| Ellesmere, Baffin, Lexa, Greenland <br>'''{{\\|Polaris}}''' 10/11/12, 22 ('''Vega M''') || GCN4.x ||  DCE 11.2 || RX 460/470/480, RX 540/550/560/570/580/590, Pro WX 3200
 +
|-
 +
! {{\\|Vega}}
 +
| '''Vega''' 10/11/12, 20 || GCN5.x || DCE 12.x || RX Vega 56, RX Vega 64, Radeon Vega II, Radeon VII
 +
|-
 +
! {{\\|Vega}}
 +
| Radeon Vega 3/6/8/10/11 <br>({{amd|Raven Ridge|l=core}}) || GCN5.x || DCN 1.0 || {{amd|Raven Ridge|l=core}} ([[Zen]]), {{amd|Picasso|l=core}} (Zen+) APU series
 +
|-
 +
! {{\\|Vega}}
 +
| Radeon RX Vega 5/6/7/8 <br>({{amd|Renoir|l=core}}) || GCN5.x || DCN 2.1 || {{amd|Renoir|l=core}} (Zen 2), {{amd|Lucienne|l=core}} (Zen 2), {{amd|Cezanne|l=core}} (Zen 3) APU series
 +
|-
 +
|
 +
|-
 +
! {{\\|Navi}}
 +
| Navi 10 (Fighter)/12/14 (Gaming) || RDNA 1.0 || DCN 2.0 || Radeon RX 5500 (XT), RX 5600 (XT), RX 5700 (XT)
 +
|-
 +
! {{\\|Navi}} II
 +
| Navi 21 (Sienna Cichlid)/22 (Navy Flounder)/ <br>23 (Dimgrey Cavefish)/24 (Beige Goby) || RDNA 2.0 || DCN 3.0 || RX 6500 XT, RX 6600 (XT), RX 6650 XT, RX 6700 (XT), <br>RX 6750 XT, RX 6800 (XT), RX 6900 XT, RX 6950 XT
 +
|-
 +
! {{\\|Navi}} III
 +
| Navi 31 (Plum Bonito)/32 (Wheat Nas)/ <br>33 (Hotpink Bonefish) || RDNA 3.0 || DCN 3.2 || RX 7000 series • Radeon RX 7400/7500 (XT)/7600 (XT)/ <br>7600 (M/S)/7650 (GRE)/7700 (XT/S)/7800 (XT/M)/7900 (XT) <br>• Radeon PRO W7400/W7500/W7600/W7700/W7800/W7900
 +
|-
 +
! {{\\|Navi}} III
 +
| {{amd|Phoenix|l=core}} (FP8), {{amd|Phoenix 2|l=core}} (FC-LGA1718), <br>{{amd|Hawk Point|l=core}} (FP8) || RDNA 3.0 || DCN 3.1.4 || Phoenix Point (Zen 4) APU series <br>• [[Ryzen 5]] 7540U, 7640U/HS, 8740U, <br>• [[Ryzen 7]] 7840U/H/HS, 7940HS, 8700G <br>• Ryzen Z1 (Extreme)/Z2, Radeon 740M/760M/780M
 +
|-
 +
! {{\\|Navi}} III
 +
| {{amd|Strix Point|l=core}} (FP8), {{amd|Strix Halo|l=core}} (FP11), <br>{{amd|Krackan Point|l=core}} (FP8) || RDNA 3.5 || DCN 3.5 || Strix Point (Zen 5) APU series • [[Ryzen]] AI 9 365/370, Z2 Extreme <br>Radeon 860M/880M/890M,  Radeon 8040S/8050S/8060S <!-- Also called RDNA 3+ or RDNA3 refresh, Ryzen AI Z2 Extreme GPU -->
 +
|-
 +
! {{\\|Navi}} IV
 +
| Navi 44/48 || RDNA 4.0 || DCN 3.2 || RX 9060 (XT), RX 9070 (GRE/XT), Radeon AI PRO R9700
 +
|}
  
 
== Generation ==
 
== Generation ==
Line 90: Line 137:
 
! Radeon 780M  
 
! Radeon 780M  
 
| Phoenix || PCIe 4.0 x8 || System Shared / DDR5 || 2900 MHz || System Shared || 768 / 48 / 32 || Jan 31, 2024  
 
| 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  
 
! Radeon 860M  
−
| Krackan Point || PCIe 4.0 x8 || System Shared / DDR5 || 3000 MHz || System Shared || 512 / 32 / 8 || Mar 15, 2025
+
| Krackan Point || PCIe 4.0 x8 || System Shared / DDR5 || 3000 MHz || System Shared || 512 / 32 / 16 || Mar 15, 2025
 
|-
 
|-
 
! Radeon 880M  
 
! Radeon 880M  
Line 102: Line 152:
  
 
=== Comparison of RDNA chips ===
 
=== Comparison of RDNA chips ===
−
<!--
 
−
<pre>
 
−
<div style="overflow-x:scroll">
 
−
{| class="wikitable" style="font-size: 85%; text-align: center;"
 
−
|+RDNA discrete GPU chips
 
−
|-
 
−
! style="min-width: 12em;" | Microarchitecture
 
−
! colspan="3" | RDNA&nbsp;1
 
−
! colspan="4" | RDNA&nbsp;2
 
−
! colspan="3" | RDNA&nbsp;3
 
−
! colspan="2" | RDNA&nbsp;4
 
−
|-
 
−
! Chip
 
−
! Navi&nbsp;10<ref>{{Cite web |title=AMD Navi 10 GPU Specs |url=https://www.techpowerup.com/gpu-specs/amd-navi-10.g861 |access-date=November 5, 2022 |website=TechPowerUp}}</ref>
 
−
! Navi&nbsp;12<ref>{{Cite web |title=AMD Navi 12 GPU Specs |url=https://www.techpowerup.com/gpu-specs/amd-navi-12.g922 |access-date=November 5, 2022 |website=TechPowerUp}}</ref>
 
−
! Navi&nbsp;14<ref>{{Cite web |title=AMD Navi 14 GPU Specs |url=https://www.techpowerup.com/gpu-specs/amd-navi-14.g919 |access-date=November 5, 2022 |website=TechPowerUp}}</ref>
 
−
! Navi&nbsp;21<ref>{{Cite web |title=AMD Navi 21 GPU Specs |url=https://www.techpowerup.com/gpu-specs/amd-navi-21.g923 |access-date=November 7, 2022 |website=TechPowerUp}}</ref>
 
−
! Navi&nbsp;22<ref>{{Cite web |title=AMD Navi 22 GPU Specs |url=https://www.techpowerup.com/gpu-specs/amd-navi-22.g951 |access-date=November 7, 2022 |website=TechPowerUp}}</ref>
 
−
! Navi&nbsp;23<ref>{{Cite web |title=AMD Navi 23 GPU Specs |url=https://www.techpowerup.com/gpu-specs/amd-navi-23.g926 |access-date=November 7, 2022 |website=TechPowerUp}}</ref>
 
−
! Navi&nbsp;24<ref>{{Cite web |title=AMD Navi 24 GPU Specs |url=https://www.techpowerup.com/gpu-specs/amd-navi-24.g965 |access-date=November 7, 2022 |website=TechPowerUp}}</ref>
 
−
! Navi&nbsp;31<ref>{{Cite web |title=AMD Navi 31 GPU Specs |url=https://www.techpowerup.com/gpu-specs/amd-navi-31.g998 |access-date=November 7, 2022 |website=TechPowerUp}}</ref><ref>{{Cite press release |title=AMD Unveils World's Most Advanced Gaming Graphics Cards, Built on Groundbreaking AMD RDNA 3 Architecture with Chiplet Design |url=https://www.amd.com/en/press-releases/2022-11-03-amd-unveils-world-s-most-advanced-gaming-graphics-cards-built |website=AMD |date=November 3, 2022}}</ref>
 
−
! Navi&nbsp;32<ref>{{Cite web |title=AMD Navi 32 GPU Specs |url=https://www.techpowerup.com/gpu-specs/amd-navi-32.g1000 |access-date=August 25, 2023 |website=TechPowerUp}}</ref>
 
−
! Navi&nbsp;33<ref>{{Cite web |title=AMD Navi 33 GPU Specs |url=https://www.techpowerup.com/gpu-specs/amd-navi-33.g1001 |access-date=November 22, 2022 |website=TechPowerUp}}</ref>
 
−
! Navi&nbsp;44<ref>{{Cite web |title=AMD Navi 44 GPU Specs |url=https://www.techpowerup.com/gpu-specs/amd-navi-44.g1070 |access-date=June 19, 2025 |website=TechPowerUp}}</ref>
 
−
! Navi&nbsp;48<ref>{{Cite web |title=AMD Navi 48 GPU Specs |url=https://www.techpowerup.com/gpu-specs/amd-navi-48.g1071 |access-date=May 9, 2025 |website=TechPowerUp}}</ref>
 
−
|-
 
−
! [[Code name]]
 
−
| ''Gaming''
 
−
|
 
−
| ''Fighter''
 
−
| ''Sienna Cichlid''
 
−
| ''Navy Flounder''
 
−
| ''Dimgrey Cavefish''
 
−
| ''Beige Goby''
 
−
| ''Plum Bonito''
 
−
| ''Wheat Nas''
 
−
| ''Hotpink Bonefish''
 
−
|
 
−
|
 
−
|-
 
−
! LLVM target<ref>{{cite web |title=User Guide for AMDGPU Backend — LLVM 22.0.0git documentation |url=https://llvm.org/docs/AMDGPUUsage.html |website=llvm.org}}</ref><ref>{{cite web |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>
 
−
| gfx1010
 
−
| gfx1011
 
−
| gfx1012
 
−
| gfx1030
 
−
| gfx1031
 
−
| gfx1032
 
−
| gfx1034
 
−
| gfx1100
 
−
| gfx1101
 
−
| gfx1102
 
−
| gfx1200
 
−
| gfx1201
 
−
|-
 
−
! [[Semiconductor device fabrication|Fab]]
 
−
| colspan="6" | [[TSMC]]&nbsp;[[7 nm process|N7]]
 
−
| TSMC&nbsp;[[7 nm process|N6]]
 
−
| colspan="2" | TSMC&nbsp;[[5 nm process|N5]]&nbsp;(GCD), TSMC&nbsp;N6&nbsp;(MCD)
 
−
| TSMC&nbsp;N6
 
−
| colspan="2" |TSMC&nbsp;N4
 
−
|-
 
−
! Package
 
−
| colspan="7" | [[Integrated circuit|Monolithic]]
 
−
| colspan="2" |[[Multi-chip module|Multi-chip module (MCM)]]
 
−
| colspan="3" |Monolithic
 
−
|-
 
−
! Die&nbsp;size (mm<sup>2</sup>)
 
−
| 251 || {{Unknown}} || 158 || 520 || 335 || 237 || 107 || ~531 || ~350 || 204 || 199 || 357
 
−
|-
 
−
! Graphics compute dies
 
−
| colspan="7" {{N/a}}
 
−
| colspan="2" | 1
 
−
| colspan="3" {{N/a}}
 
−
|-
 
−
! Memory cache dies
 
−
| colspan="7" {{N/a}}
 
−
| 6
 
−
| 4
 
−
| colspan="3" {{N/a}}
 
−
|-
 
−
! {{abbr|GCD|Graphics compute die}}&nbsp;size (mm<sup>2</sup>)
 
−
| colspan="7" {{N/a}}
 
−
| 306
 
−
| 200
 
−
| colspan="3" {{N/a}}
 
−
|-
 
−
! {{abbr|MCD|Memory cache die}}&nbsp;size (mm<sup>2</sup>)
 
−
| colspan="7" {{N/a}}
 
−
| colspan="2" | 37.5
 
−
| colspan="3" {{N/a}}
 
−
|-
 
−
! Transistors (billions)
 
−
| 10.3 || {{Unknown}} || 6.4 || 26.8 || 17.2 || 11.06 || 5.4 || 57.7 || 28.1 || 13.3 || 29.7 ||53.9
 
−
|-
 
−
! Transistor density<br />(MTr/mm<sup>2</sup>)
 
−
| 41.0 || {{Unknown}} || 40.5 || 51.5 || 51.3 || 46.7 || 50.5 || 109.2&nbsp;(MCM)<br />132.4&nbsp;(GCD)<ref>{{Cite web |author=btarunr |date=November 4, 2022 |title=AMD Announces the $999 Radeon RX 7900 XTX... (endnote RX-819) |url=https://www.techpowerup.com/300632/amd-announces-the-usd-999-radeon-rx-7900-xtx-and-usd-899-rx-7900-xt-5nm-rdna3-displayport-2-1-fsr-3-0-fluidmotion |website=TechPowerUp}}</ref>|| 81.2 || 65.2 || 149.2 || 151
 
−
|-
 
−
! Shader engines
 
−
| colspan="2" | 2 || 1 || 4<ref name="3DCenter Navi2x">{{cite web |date=January 24, 2022 |title=Launch-Analyse AMD Radeon RX 6500 XT |url=https://www.3dcenter.org/artikel/launch-analyse-amd-radeon-rx-6500-xt |website=3DCenter.org |language=de |access-date=November 29, 2022}}</ref> || colspan="2" | 2<ref name="3DCenter Navi2x" /> || 1<ref name="3DCenter Navi2x" /> || 6 || {{TBA}} || colspan="2" | 2 || 4
 
−
|-
 
−
! Shader arrays
 
−
| colspan="2" | 4 || 2 || 8 || colspan="2" | 4 || 2 || 12 || {{TBA}} || colspan="2" | 4 || 8
 
−
|-
 
−
! Workgroup processors
 
−
| colspan="2" | 20
 
−
| 12 || 40 || 20 || 16 || 8 || 48 || 30 || colspan="2" | 16 || 32
 
−
|-
 
−
! Compute units
 
−
| colspan="2" | 40
 
−
| 24 || 80 || 40 || 32 || 16 || 96 || 60 || colspan="2" | 32 || 64
 
−
|-
 
−
! [[Unified shader model|Stream processors]]
 
−
| colspan="2" |2560 || 1536 || 5120 || 2560 || 2048 || 1024 || 6144 || 3840 || colspan="2" | 2048 || 4096
 
−
|-
 
−
! [[Texture mapping unit]]s
 
−
| colspan="2" |160 || 96 || 320 || 160 || 128 || 64 || 384 || 240 || colspan="2" | 128 || 256
 
−
|-
 
−
! [[Render output unit]]s
 
−
| colspan="2" |64 || 32 || 128
 
−
| colspan="2" |64 || 32 || 192 || 96<ref>{{Cite web |last=Walton |first=Jarred |date=June 5, 2023 |title=AMD RDNA 3 GPU Architecture Deep Dive: The Ryzen Moment for GPUs |url=https://www.tomshardware.com/news/amd-rdna-3-gpu-architecture-deep-dive-the-ryzen-moment-for-gpus |website=Tom's Hardware |language=en-US |access-date=September 11, 2023}}</ref> || colspan="2" | 64 || 128
 
−
|-
 
−
! [[Ray tracing (graphics)|RT accelerators]]
 
−
| colspan="3" {{N/a}}
 
−
| 80 || 40 || 32 || 16 || 96 || 60 || colspan="2" | 32 || 64
 
−
|-
 
−
! [[AI accelerator]]s{{efn|GPU matrix-multiplication units, not to be confused with the XDNA NPU.}}
 
−
| colspan="7" {{N/a}}
 
−
| 192 || 120 || colspan="2" | 64 || 128
 
−
|-
 
−
! L0&nbsp;[[Cache (computing)#Examples of hardware caches|cache]] (KB)
 
−
| colspan="7" | 32&nbsp;per Workgroup processor (WGP)
 
−
| colspan="5" | 64&nbsp;per WGP
 
−
|-
 
−
! L1&nbsp;cache (KB)
 
−
| colspan="7" | 128&nbsp;per Shader array (SA)
 
−
| colspan="3" | 256&nbsp;per SA
 
−
| colspan="2" | 128&nbsp;per SA
 
−
|-
 
−
! L2&nbsp;cache (MB)
 
−
| 8 || 4 || 2 || 4 || 3 || 2 || 1 || 6 || 4 || 2 || 4 || 8
 
−
|-
 
−
! L3&nbsp;cache (MB)
 
−
| colspan="3" {{N/a}}
 
−
| 128 || 96 || 32 || 16 || 96 || 64 || colspan="2" | 32 || 64
 
−
|-
 
−
! Memory type
 
−
| [[GDDR6 SDRAM|GDDR6]] || [[High Bandwidth Memory#HBM2|HBM2]] || colspan="10" | GDDR6
 
−
|-
 
−
! Memory bus (bits)
 
−
| 256 || 2048 || 128 || 256 || 192 || 128 || 64 || 384 || 256 || colspan="2" | 128 || 256
 
−
|-
 
−
! Display Core Next
 
−
| colspan="3" | 2.0.0 || colspan="2" | 3.0.0 || 3.0.2 || 3.0.3 || colspan="2" | 3.2.0 || 3.2.1 || colspan="2" | 4.0.1
 
−
|-
 
−
! [[Video Core Next]]
 
−
| 2.0.0 || colspan="2" | 2.0.2 || colspan="2" | 3.0.0 || 3.0.16 || 3.0.33 || colspan="2" | 4.0.0 || 4.0.4 || colspan="2" | 5.0.0
 
−
|-
 
−
! Launch
 
−
| {{dts|2019|July|7|format=my|abbr=on}}
 
−
| {{dts|2020|June|15|format=my|abbr=on}}
 
−
| {{dts|2019|October|7|format=my|abbr=on}}
 
−
| {{dts|2020|November|18|format=my|abbr=on}}
 
−
| {{dts|2021|March|18|format=my|abbr=on}}
 
−
| {{dts|2021|May|31|format=my|abbr=on}}
 
−
| {{dts|2022|January|2|format=my|abbr=on}}
 
−
| {{dts|2022|December|13|format=my|abbr=on}}
 
−
| {{dts|2023|September|6|format=my|abbr=on}}
 
−
| {{dts|2023|January|4|format=my|abbr=on}}
 
−
| {{dts|2025|June||format=my|abbr=on}}
 
−
| {{dts|2025|March||format=my|abbr=on}}
 
−
|-
 
−
! Introduced with
 
−
| style="vertical-align:top; text-align: left;" | [[Radeon RX 5000 series#Desktop|RX&nbsp;5700&nbsp;(XT)]]
 
−
| style="vertical-align:top; text-align: left;" | [[Radeon Pro#Radeon Pro 5000M series (for Apple MacBook Pro)|Pro&nbsp;5600M]]
 
−
| style="vertical-align:top; text-align: left;" | {{ubl|[[Radeon RX 5000 series#Desktop|RX 5500]]|[[Radeon RX 5000 series#Mobile|RX&nbsp;5500M]]}}
 
−
| style="vertical-align:top; text-align: left;" | [[Radeon RX 6000 series#Desktop|RX&nbsp;6800&nbsp;(XT)]]
 
−
| style="vertical-align:top; text-align: left;" | [[Radeon RX 6000 series#Desktop|RX&nbsp;6700&nbsp;XT]]
 
−
| style="vertical-align:top; text-align: left;" | [[Radeon RX 6000 series#Mobile|RX&nbsp;6600M]]
 
−
| style="vertical-align:top; text-align: left;" | {{ubl|[[Radeon RX 6000 series#Mobile|RX 6300M]]|[[Radeon RX 6000 series#Mobile|RX&nbsp;6500M]]}}
 
−
| style="vertical-align:top; text-align: left;" | [[Radeon RX 7000 series#Desktop|RX&nbsp;7900&nbsp;XT(X)]]
 
−
| style="vertical-align:top; text-align: left;" | {{ubl|[[Radeon RX 7000 series#Desktop|RX 7700 XT]]|[[Radeon RX 7000 series#Desktop|RX&nbsp;7800&nbsp;XT]]}}
 
−
| style="vertical-align:top; text-align: left;" | {{ubl|[[Radeon RX 7000 series#Mobile|RX 7600S]]|[[Radeon RX 7000 series#Mobile|RX&nbsp;7600M&nbsp;(XT)]]|[[Radeon RX 7000 series#Mobile|RX 7700S]]}}
 
−
| style="vertical-align:top; text-align: left;" | [[Radeon RX 9000 series#Desktop|RX&nbsp;9060&nbsp;XT]]
 
−
| style="vertical-align:top; text-align: left;" | [[Radeon RX 9000 series#Desktop|RX&nbsp;9070 (XT)]]
 
−
|}
 
−
</div>
 
−
</pre>
 
−
-->
 
  
 
{| class="wikitable" cellpadding="3px" style="border: 1px solid black; border-spacing: 0px; width: 100%; text-align:center;"
 
{| class="wikitable" cellpadding="3px" style="border: 1px solid black; border-spacing: 0px; width: 100%; text-align:center;"
Line 307: Line 169:
 
| 740M<hr>760M<hr>780M
 
| 740M<hr>760M<hr>780M
 
| 740M<hr>760M<hr>780M
 
| 740M<hr>760M<hr>780M
−
| Radeon<br>880M<hr>890M
+
| 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
 
| 8040S<hr>8050S<hr>8060S
−
| Radeon<br>860M
+
| Radeon<br>840M<hr>860M
 
|-
 
|-
 
! Code name
 
! Code name
Line 319: Line 181:
 
| Phoenix  
 
| Phoenix  
 
| Hawk Point
 
| 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> <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>
+
| ''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>
 
| ''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>
 
|''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>
 
! 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>
Line 336: Line 210:
 
! Fab process
 
! Fab process
 
| colspan="5" | [[TSMC]] [[7 nm process|N6]]
 
| colspan="5" | [[TSMC]] [[7 nm process|N6]]
−
| colspan="2" |
+
| colspan="2" | [[TSMC]] [[5 nm process|N4]]
−
| colspan="3" | [[TSMC]] [[5 nm process|N4]]
+
| colspan="3" | [[TSMC]] [[5 nm process|N4P]]
 
|-
 
|-
 
! Package
 
! Package
Line 347: Line 221:
 
|-
 
|-
 
! Die&nbsp;size (mm<sup>2</sup>)
 
! Die&nbsp;size (mm<sup>2</sup>)
−
| || ||
+
| || || || ||  
−
| || || || || TBA || 308 || TBA
+
| colspan="2" | 178
 +
| 232 || 232 / 308 || TBA
 
|-
 
|-
 
! Workgroup processors <br>(WGP)
 
! Workgroup processors <br>(WGP)
 
| || ||
 
| || ||
−
| || || || || 8 || 20 || 4
+
| || || ||  
 +
| 8 || 20 || 4
 
|-
 
|-
 
! Compute units (CU)
 
! Compute units (CU)
 
| || ||
 
| || ||
−
| || || ||
+
| ||  
−
| 16 || 40 || 8
+
| 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)
 
! Stream processors <br>(Cores)
 
| 384<hr>768 || 128 || 128  
 
| 384<hr>768 || 128 || 128  
−
| 384<hr>768 || 128 || 256<hr>512<hr>768 || 256<hr>512<hr>768
+
| 384<hr>768 || 128  
−
| 768<hr>1024 || 2560 || 512
+
| 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)
 
! Texture mapping units <br>(TMU)
 
| 24<hr>48 || 8 || 8  
 
| 24<hr>48 || 8 || 8  
−
| 24<hr>48 || 8 || 16<hr>32<hr>48 || 16<hr>32<hr>48
+
| 24<hr>48 || 8  
−
| 48<hr>64 || 160 || 32
+
| 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)
 
! Render output units <br>(ROP)
 
| 16<hr>32 || 8 || 4  
 
| 16<hr>32 || 8 || 4  
−
| 16<hr>32 || 4 || 8<hr>16<hr>32 || 8<hr>16<hr>32
+
| 16<hr>32 || 4  
−
| 16<hr>32 || 64 ||8
+
| 8<hr>16<hr>32 || 8<hr>16<hr>32
 +
| 24<hr>32 || 32<hr>64<hr>80 || 8<hr>16
 
|-
 
|-
 
! RT accelerators
 
! RT accelerators
 
| || ||
 
| || ||
−
| || || ||
+
| ||  
−
| 16 || 40 || 8
+
| 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
 
! [[AI accelerator]]s
Line 386: Line 267:
 
! L0&nbsp;cache (KB)
 
! L0&nbsp;cache (KB)
 
| colspan="5" | 32 KB per WGP (Workgroup processor)
 
| colspan="5" | 32 KB per WGP (Workgroup processor)
−
| colspan="5" | 64 KB per WGP
+
| colspan="2" | 64 KB per WGP
 +
| colspan="3" | 64 KB per WGP
 
|-
 
|-
 
! L1&nbsp;cache (KB)
 
! L1&nbsp;cache (KB)
 
| colspan="5" | 128 KB per SA (Shader array)
 
| colspan="5" | 128 KB per SA (Shader array)
−
| colspan="5" | 256 KB per SA
+
| colspan="2" | 256 KB per SA
 +
| colspan="3" | 256 KB per SA
 
|-
 
|-
 
! L2&nbsp;cache (MB)
 
! L2&nbsp;cache (MB)
 
| || ||
 
| || ||
−
| || || || || 2 || 8 || 1
+
| || || 2 || 2
 +
| 2 || 8 || 2
 
|-
 
|-
 
! L3&nbsp;cache (MB)
 
! L3&nbsp;cache (MB)
 
| || ||
 
| || ||
−
| || || || || 0 || 32 || 0  
+
| || || 0 / 16 (Z1)|| 0
 +
| 0 || 64 || 0  
 
|-
 
|-
 
! Memory type
 
! Memory type
Line 406: Line 291:
 
| DDR5 /<br>LPDDR5
 
| DDR5 /<br>LPDDR5
 
| GDDR6
 
| GDDR6
−
| colspan="5" | DDR5 / LPDDR5(X)
+
| colspan="2" | DDR5 / LPDDR5(X)
 +
| colspan="3" | DDR5 / LPDDR5(X)
 
|-
 
|-
 
! Memory bus (bits)  
 
! Memory bus (bits)  
−
| colspan="3" | 128 || colspan="2" | 128 || colspan="2" | 128  
+
| colspan="3" | 128  
 +
| colspan="2" | 128  
 +
| colspan="2" | 128  
 
| 128 || 128 / 256 || 128  
 
| 128 || 128 / 256 || 128  
 
|-
 
|-
 
! Display Core Next
 
! Display Core Next
−
| colspan="2" | ||
+
| colspan="2" | || || ||  
−
| || || colspan="2" | || 3.1.4 || 3.5.0 || 3.5.0
+
| colspan="2" |  
 +
| 3.1.4 || 3.5.0 || 3.5.0
 
|-
 
|-
 
! Video Core Next
 
! Video Core Next
−
| colspan="2" | ||
+
| colspan="2" | || || ||  
−
| || || colspan="2" | || 4.0.2 || 4.0.5 || 4.0.5
+
| colspan="2" |  
 +
| 4.0.2 || 4.0.5 || 4.0.5
 
|-
 
|-
 
! Launch
 
! Launch
 
| January <br>2022
 
| January <br>2022
 
| colspan="2" | September <br>2022
 
| colspan="2" | September <br>2022
−
| colspan="3" | January <br>2023
+
| colspan="2" | January <br>2023
−
| December <br>2023
+
| January <br>2023 || December <br>2023
−
| July <br>2024
+
| July <br>2024 || January <br>2025 || March <br>2025
−
| January <br>2025
 
−
| March <br>2025
 
 
|}
 
|}
  

Latest revision as of 08:10, 20 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

Family[edit]

Family Chipset name Microarchitecture ISA Product name
Southern Islands Cape Verde, Hainan, Oland, Pitcairn, Tahiti GCN1.0+ DCE 6.x HD7750 - HD7970, R9 270, R9 280, R9 370X, R7 240, R7 250
Sea Islands Bonaire, Hawaii, Kabini, Kaveri, Mullins GCN2.x DCE 8.x HD7790, R7 260, R9 290, R7 360, R9 390
Volcanic Islands Fiji, Iceland, Stoney, Tonga, Topaz, Wani GCN3.x DCE 10/11.x R9 285, R9 380/380X, R9 Fury, R9 Nano, R9 Fury X, Pro Duo
Arctic Islands Ellesmere, Baffin, Lexa, Greenland
Polaris 10/11/12, 22 (Vega M) 		GCN4.x DCE 11.2 RX 460/470/480, RX 540/550/560/570/580/590, Pro WX 3200
Vega Vega 10/11/12, 20 GCN5.x DCE 12.x RX Vega 56, RX Vega 64, Radeon Vega II, Radeon VII
Vega Radeon Vega 3/6/8/10/11
(Raven Ridge) 		GCN5.x DCN 1.0 Raven Ridge (Zen), Picasso (Zen+) APU series
Vega Radeon RX Vega 5/6/7/8
(Renoir) 		GCN5.x DCN 2.1 Renoir (Zen 2), Lucienne (Zen 2), Cezanne (Zen 3) APU series
Navi Navi 10 (Fighter)/12/14 (Gaming) RDNA 1.0 DCN 2.0 Radeon RX 5500 (XT), RX 5600 (XT), RX 5700 (XT)
Navi II Navi 21 (Sienna Cichlid)/22 (Navy Flounder)/
23 (Dimgrey Cavefish)/24 (Beige Goby) 		RDNA 2.0 DCN 3.0 RX 6500 XT, RX 6600 (XT), RX 6650 XT, RX 6700 (XT),
RX 6750 XT, RX 6800 (XT), RX 6900 XT, RX 6950 XT
Navi III Navi 31 (Plum Bonito)/32 (Wheat Nas)/
33 (Hotpink Bonefish) 		RDNA 3.0 DCN 3.2 RX 7000 series • Radeon RX 7400/7500 (XT)/7600 (XT)/
7600 (M/S)/7650 (GRE)/7700 (XT/S)/7800 (XT/M)/7900 (XT)
• Radeon PRO W7400/W7500/W7600/W7700/W7800/W7900
Navi III Phoenix (FP8), Phoenix 2 (FC-LGA1718),
Hawk Point (FP8) 		RDNA 3.0 DCN 3.1.4 Phoenix Point (Zen 4) APU series
• Ryzen 5 7540U, 7640U/HS, 8740U,
• Ryzen 7 7840U/H/HS, 7940HS, 8700G
• Ryzen Z1 (Extreme)/Z2, Radeon 740M/760M/780M
Navi III Strix Point (FP8), Strix Halo (FP11),
Krackan Point (FP8) 		RDNA 3.5 DCN 3.5 Strix Point (Zen 5) APU series • Ryzen AI 9 365/370, Z2 Extreme
Radeon 860M/880M/890M, Radeon 8040S/8050S/8060S
Navi IV Navi 44/48 RDNA 4.0 DCN 3.2 RX 9060 (XT), RX 9070 (GRE/XT), Radeon AI PRO R9700

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=104004"
    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) +