Radeon 600 series

Series of video cards From Wikipedia, the free encyclopedia

The AMD Radeon 600 series is a series of graphics processors developed by AMD. Its cards are desktop and mobile rebrands of previous generation Polaris cards, available only for OEMs.[2] The series is targeting the entry-level segment and launched on August 13, 2019.[3]

Release dateAugust 13, 2019 (6 years ago) (2019-08-13)
CodenamePolaris
ArchitectureGCN 1st gen
GCN 3rd gen
GCN 4th gen
Transistors
  • 690M (Banks) 28 nm
  • 1.550M (Polaris 24) 28 nm
  • 2.200M (Polaris 23) 14 nm
Quick facts Release date, Codename ...
AMD Radeon 600 series
Release dateAugust 13, 2019 (6 years ago) (2019-08-13)
CodenamePolaris
ArchitectureGCN 1st gen
GCN 3rd gen
GCN 4th gen
Transistors
  • 690M (Banks) 28 nm
  • 1.550M (Polaris 24) 28 nm
  • 2.200M (Polaris 23) 14 nm
Fabrication processTSMC 28 nm (CMOS)
Samsung/GloFo 14 nm (FinFET)
Cards
Entry-levelRadeon 610
Radeon 620
Radeon 625
Radeon 630
Radeon RX 640
API support
Direct3D
OpenCLOpenCL 2.1
OpenGLOpenGL 4.6
VulkanVulkan 1.2 (GCN 1st gen and GCN 3rd gen for Windows)[1]
Vulkan 1.3 (GCN 4th gen for Windows, GCN 1st gen or newer for Linux)
SPIR-V
History
PredecessorRadeon 500 series
VariantRadeon RX 5000 series
Support status
GCN 4 cards supported
Close

Products

Desktop

More information Model (Code name), Release date & Price ...
Model
(Code name)		 Release date
& Price		 Architecture
& fab		 Transistors
& die size		 Core Fillrate[a][b][c] Processing power[a][d]
(GFLOPS)		 Memory TBP Bus interface
Config[e] Clock[a]
(MHz)		 Texture
(GT/s)		 Pixel
(GP/s)		 Single Double Size
(GB)		 Bandwidth
(GB/s)		 Bus type
& width		 Clock
(MT/s)
Radeon 630
(Polaris 23)[6][7]		 Aug 13, 2019
OEM[8]		 GCN 4
GloFo 14 nm[f]		 2.2×109
103 mm2		 512:32:8
8 CU		 1082
1219		 34.62
38.98		 8.65
9.75		 1,108
1,248		 69.24
78.01		 2
4		 48.0 GDDR5
64-bit		 6000 50 W PCIe 3.0 ×8
Radeon RX 640
(Polaris 23)[10][11]		 512:40:16
8 CU		 1082
1287		 43.28
51.48		 17.31
20.59		 1,385
1,647		 86.56
102.9		 56.0 7000
640:40:16
10 CU
Close
  1. [a]
    Boost values (if available) are stated below the base value in italic.
  2. [b]
    Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base (or boost) core clock speed.
  3. [c]
    Pixel fillrate is calculated as the number of Render Output Units multiplied by the base (or boost) core clock speed.
  4. [d]
    Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
  5. [e]
    Unified shaders : Texture mapping units : Render output units and Compute units (CU)
  6. [f]
    GlobalFoundries' 14 nm 14LPP FinFET process is second-sourced from Samsung Electronics.[9]

Laptop

More information Model (Code name), Release date & price ...
Model
(Code name)		 Release date
& price		 Architecture
& fab		 Transistors
& die size		 Core Fillrate[a][b][c] Processing power[a][d]
(GFLOPS)		 Memory TBP Bus interface
Config[e] Clock[a]
(MHz)		 Texture
(GT/s)		 Pixel
(GP/s)		 Single Double Size
(GB)		 Bandwidth
(GB/s)		 Bus type
& width		 Clock
(MT/s)
Radeon 610
(Banks)[12]		 Aug 13, 2019
OEM[13]		 GCN 1[14]
TSMC 28 nm		 6.9×108
56 mm2		 320:20:4
5 CU
1030
20.60
8.24
659.2
41.20		 2
4		 36.0 GDDR5
64-bit		 4500 50 W PCIe 3.0 ×8
Radeon 620
(Polaris 24)[15]		 GCN 3[16]
TSMC 28 nm		 1.55×109
125 mm2		 320:20:8
6 CU		 730
1024		 17.52
24.58		 5.84
8.19		 560.6
786.4		 35.04
49.15		 14.4 DDR3
64-bit		 1800
384:24:8
6 CU		 36.0 GDDR5
64-bit		 4500
Radeon 625
(Polaris 24)[17]
Radeon 630
(Polaris 23)[18][19]		 GCN 4
GloFo 14 nm[f]		 2.2×109
103 mm2		 512:32:8
8 CU		 1082
1219		 34.62
38.98		 8.65
9.75		 1,108
1,248		 69.24
78.01		 48.0 6000
Radeon RX 640
(Polaris 23)[21][22]		 512:40:16
8 CU		 1082
1287		 43.28
51.48		 17.31
20.59		 1,385
1,647		 86.56
102.9		 56.0 7000
640:40:16
10 CU
Close
  1. [a]
    Boost values (if available) are stated below the base value in italic.
  2. [b]
    Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base (or boost) core clock speed.
  3. [c]
    Pixel fillrate is calculated as the number of Render Output Units multiplied by the base (or boost) core clock speed.
  4. [d]
    Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
  5. [e]
    Unified shaders : Texture mapping units : Render output units and Compute units (CU)
  6. [f]
    GlobalFoundries' 14 nm 14LPP FinFET process is second-sourced from Samsung Electronics.[20]

See also

References

External links

Related Articles

Wikiwand AI