AMD Radeon Instinct MI60 vs AMD Radeon Instinct MI25

AMD Radeon Instinct MI60
AMD Radeon Instinct MI25
4096 Shaders
32GB HBM2
1800MHz
4096 Shaders
16GB HBM2
1500MHz
Peak AI Performance
29.49 TFLOPS
FP16
Peak AI Performance
24.58 TFLOPS
FP16
FP32
14.75 TFLOPS
FP32
12.29 TFLOPS
FP16
29.49 TFLOPS
FP16
24.58 TFLOPS
Form Factor
PCIe Card
2.0-Slots
Form Factor
PCIe Card
2.0-Slots
TDP
300W
TDP
300W
Power Connectors
1x 6-Pin
1x 8-Pin
Power Connectors
-
2x 8-Pin

Peak AI Performance

  • 20% faster vs Radeon Instinct MI25
  • 17% slower vs Radeon Instinct MI60
Radeon Instinct MI60 - 29.49 TFLOPS FP16
x1.2
Radeon Instinct MI25 - 24.58 TFLOPS FP16
x1

FP32

  • 20% faster vs Radeon Instinct MI25
  • 17% slower vs Radeon Instinct MI60
Radeon Instinct MI60 - 14.75 TFLOPS FP32
x1.2
Radeon Instinct MI25 - 12.29 TFLOPS FP32
x1

FP16

  • 20% faster vs Radeon Instinct MI25
  • 17% slower vs Radeon Instinct MI60
Radeon Instinct MI60 - 29.49 TFLOPS FP16
x1.2
Radeon Instinct MI25 - 24.58 TFLOPS FP16
x1
  • 2.12x faster vs Radeon Instinct MI25
  • 53% slower vs Radeon Instinct MI60
Radeon Instinct MI60 - 1024GB/s
x2.12
Radeon Instinct MI25 - 483.8GB/s
x1
  • Same TDP vs Radeon Instinct MI25
  • Same TDP vs Radeon Instinct MI60
Radeon Instinct MI60 - 300W
x1
Radeon Instinct MI25 - 300W
x1
GB6 OpenCL N/A
0%
GB6 Vulkan N/A
0%
Manufacturer
AMD
Manufacturer
AMD
Chip Designer
AMD
Chip Designer
AMD
Architecture
GCN 5
Architecture
GCN 5
Family
Instinct
Family
Instinct
Codename
Moonshot
Vega 20
Variant
Vega 20 XT GL
Codename
Greenland
Vega 10
Variant
Vega 10 XT GL
Market Segment
Server
Market Segment
Server
Release Date
11/18/2018
Release Date
6/20/2017
Foundry
TSMC
Foundry
GlobalFoundries
Fabrication Node
N7
Fabrication Node
14LPP
Die Size
331 mm²
Die Size
486 mm²
Transistor Count
13.2 Billion
Transistor Count
12.5 Billion
Transistor Density
39.97M/mm²
Transistor Density
25.72M/mm²
Form
PCIe Card
Form
PCIe Card
Shading Units
4096 Shaders
Shading Units
4096 Shaders
Texture Mapping Units
256 TMUs
Texture Mapping Units
256 TMUs
Render Output Units
64 ROPs
Render Output Units
64 ROPs
Compute Units
64 CUs
Compute Units
64 CUs
1500MHz Base
1800MHz
1400MHz Base
1500MHz
Peak AI Performance
29.49 TFLOPS
FP16
Peak AI Performance
24.58 TFLOPS
FP16
FP16
29.49 TFLOPS
FP16
24.58 TFLOPS
FP32
14.75 TFLOPS
FP32
12.29 TFLOPS
FP64
7.37 TFLOPS
FP64
770 GFLOPS
Pixel Fillrate
115.2 GPixel/s
Pixel Fillrate
96 GPixel/s
Texture Fillrate
460.8 GTexel/s
Texture Fillrate
384 GTexel/s
L1
16KB/CU
L1
16KB/CU
L2
4MB Shared
L2
4MB Shared
32GB
HBM2
ECC
16GB
HBM2
ECC
Bus Width
4096Bit
Bus Width
2048Bit
Clock
1000MHz
Transfer Rate
2GT/s
Bandwidth
1024GB/s
Clock
945MHz
Transfer Rate
1.9GT/s
Bandwidth
483.8GB/s
TDP
300W
TDP
300W
1x mini-DisplayPort 1.4
1x mini-DisplayPort 1.4
Max Resolution
7680x4320
Max Resolution
7680x4320
Max Resolution Refresh Rate
60Hz
Max Resolution Refresh Rate
60Hz
Variable Refresh Rate
FreeSync
Variable Refresh Rate
FreeSync
Display Stream Compression (DSC)
Not Supported
Display Stream Compression (DSC)
Not Supported
Multi Monitor Support
3
Multi Monitor Support
3
Content Protection
HDCP 2.2
Content Protection
HDCP 2.2
Model
VCE 4.1
Model
VCE 4.0
Codec
AVC (H.264)
HEVC (H.265)
Codec
AVC (H.264)
HEVC (H.265)
Model
UVD 7.2
Model
UVD 7.0
Codec
MPEG-1
MPEG-2
MPEG-4
JPEG
VC-1
AVC (H.264)
HEVC (H.265)
Codec
MPEG-1
MPEG-2
MPEG-4
JPEG
VC-1
AVC (H.264)
HEVC (H.265)
Direct X
12
Direct 3D
12_1
Direct X
12
Direct 3D
12_1
OpenGL
4.6
OpenCL
2.1
Vulkan
1.3
OpenGL
4.6
OpenCL
2.1
Vulkan
1.3
Shader Model
6.7
GFX
9
Shader Model
6.7
GFX
9
Power Connectors
1x 6-Pin
1x 8-Pin
Power Connectors
-
2x 8-Pin
Slots Required
2.0
PCIe Version
3.0
PCIe Lanes
16
Slots Required
2.0
PCIe Version
3.0
PCIe Lanes
16
Multi GPU Support
Supported
Type
CrossFire XDMA
Multi GPU Support
Supported
Type
CrossFire XDMA
Height
111 mm (4.37 in)
Width
267 mm (10.51 in)
Depth
37 mm (1.46 in)
Height
111 mm (4.37 in)
Width
267 mm (10.51 in)
Depth
37 mm (1.46 in)
Change Comparison