AMD Radeon E9565 vs Intel Gaudi

AMD Radeon E9565
Intel Gaudi
2304 Shaders
16GB GDDR5
1243MHz
2048 Shaders
32GB HBM2
610MHz
Peak AI Performance
5.73 TFLOPS
FP16
Peak AI Performance
159.91 TFLOPS
BF16 Tensor
FP32
5.73 TFLOPS
-
-
FP16
5.73 TFLOPS
-
-
Form Factor
PCIe Card
1.0-Slots
Form Factor
OAM Module
-
TDP
135W
TDP
350W
Power Connectors
1x 6-Pin
-
-
-
-
-
-
-
-
GB6 OpenCL N/A
0%
GB6 OpenCL N/A
0%
GB6 Metal N/A
0%
GB6 Metal N/A
0%
GB6 Vulkan N/A
0%
GB6 Vulkan N/A
0%
GB5 OpenCL N/A
0%
GB5 OpenCL N/A
0%
GB5 CUDA N/A
0%
GB5 CUDA N/A
0%
GB5 Metal N/A
0%
GB5 Metal N/A
0%
GB5 Vulkan N/A
0%
GB5 Vulkan N/A
0%
OCT 2020.1 N/A
0%
OCT 2020.1 N/A
0%
OCT Metal N/A
0%
OCT Metal N/A
0%
Peak AI Performance
5.73 TFLOPS
FP16
Peak AI Performance
159.91 TFLOPS
BF16 Tensor
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
FP16
5.73 TFLOPS
-
-
-
-
-
-
-
-
-
-
FP32
5.73 TFLOPS
-
-
-
-
-
-
FP64
360 GFLOPS
-
-
-
-
-
-
-
-
BF16
-
159.91 TFLOPS Tensor
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
Pixel Fillrate
39.776 GPixel/s
Pixel Fillrate
-
-
-
-
-
Texture Fillrate
178.992 GTexel/s
Texture Fillrate
-
Manufacturer
AMD
Manufacturer
Intel
Chip Designer
AMD
Chip Designer
Intel
Architecture
GCN 4
Architecture
Gaudi
Family
Embedded
Family
Gaudi
Codename
Ellesmere
Polaris 10
Variant
Polaris 10 XT
Codename
Gaudi
HL-2000
Variant
HL-2000
Market Segment
Server
Market Segment
Server
Release Date
9/1/2020
Release Date
6/17/2019
Foundry
GlobalFoundries
-
Foundry
TSMC
-
Fabrication Node
14LPP
-
Fabrication Node
16FF
-
Die Size
232 mm²
-
-
-
-
Transistor Count
5.7 Billion
-
-
-
Transistor Density
24.57M/mm²
-
-
-
-
Form
PCIe Card
Form
OAM Module
Shading Units
2304 Shaders
-
Shading Units
2048 Shaders
-
Texture Mapping Units
144 TMUs
Texture Mapping Units
-
Render Output Units
32 ROPs
Render Output Units
-
-
-
Tensor Cores
8 T-Cores
-
-
-
-
-
-
-
-
Compute Units
36 CUs
Compute Units
1 CU
-
-
-
-
-
-
-
-
-
-
-
1243MHz
-
-
-
610MHz
-
-
-
-
L1
-
-
16KB/CU
-
L1
-
-
-
Unknown
L2
2MB Shared
L2
Unknown
-
-
-
-
-
-
16GB
GDDR5
-
32GB
HBM2
ECC
Bus Width
256Bit
Bus Width
4096Bit
Clock
1750MHz
Transfer Rate
7GT/s
Bandwidth
224GB/s
Clock
980MHz
Transfer Rate
2GT/s
Bandwidth
1003.5GB/s
-
-
-
-
-
-
-
-
-
-
-
-
-
eSRAM
24MB
3200GB/s
-
-
TDP
135W
TDP
350W
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
6x mini-DisplayPort 1.4
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
No Ports
Max Resolution
5120x2880
Max Resolution
Unknown
Max Resolution Refresh Rate
60Hz
Max Resolution Refresh Rate
-
Variable Refresh Rate
-
FreeSync
-
Variable Refresh Rate
-
-
-
Display Stream Compression (DSC)
Not Supported
Display Stream Compression (DSC)
Not Supported
Multi Monitor Support
3
Multi Monitor Support
Unknown
Content Protection
HDCP 2.2
-
-
Model
VCE 3.0
No Encoders
-
Codec
-
-
-
-
-
-
-
-
AVC (H.264)
HEVC (H.265)
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
Model
UVD 6.3
No Decoders
Codec
MPEG-1
MPEG-2
MPEG-4
JPEG
VC-1
-
-
-
AVC (H.264)
HEVC (H.265)
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
Direct X
12
Direct 3D
12_0
-
-
-
-
OpenGL
4.6
OpenCL
2.1
Vulkan
1.3
-
-
OpenCL
3.0
-
-
Shader Model
6.7
-
-
GFX
8
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
1x Fan
Not a Card
-
-
-
Power Connectors
-
-
1x 6-Pin
-
-
-
-
-
-
-
-
-
-
-
-
Slots Required
1.0
PCIe Version
3.0
PCIe Lanes
16
-
-
PCIe Version
4.0
PCIe Lanes
16
Multi GPU Support
Supported
Type
CrossFire XDMA
Multi GPU Support
Supported
Type
RoCE
Height
111 mm (4.37 in)
Width
241 mm (9.49 in)
Depth
20 mm (0.79 in)
-
-
-
-
-
-
Change Comparison