Intel Gaudi 3 vs AMD Instinct MI250

Intel Gaudi 3
AMD Instinct MI250
16384 Shaders
128GB HBM2e
438MHz
13312 Shaders
128GB HBM2e
1700MHz
Peak AI Performance
1.84 PFLOPS
FP8 Tensor (FP32 Accumulate)
Peak AI Performance
362.09 TOPS
INT4 Tensor
FP32
14.35 TFLOPS
FP32
45.26 TFLOPS
FP16
28.7 TFLOPS
FP16
90.52 TFLOPS
Form Factor
OAM Module
-
Form Factor
OAM Module
-
TDP
900W
TDP
500W
-
-
-
-
-
-
-
-
-
-
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
1.84 PFLOPS
FP8 Tensor (FP32 Accumulate)
Peak AI Performance
362.09 TOPS
INT4 Tensor
-
-
-
-
-
-
FP8
-
-
-
1.84 PFLOPS Tensor (FP32 Accumulate)
-
-
-
-
-
-
-
FP16
28.7 TFLOPS
-
-
458.75 TFLOPS Tensor (FP32 Accumulate)
-
FP16
90.52 TFLOPS
362.09 TFLOPS Tensor (FP16 Accumulate)
-
362.09 TFLOPS Tensor (FP32 Accumulate)
-
FP32
14.35 TFLOPS
229.38 TFLOPS Tensor
-
FP32
45.26 TFLOPS
90.52 TFLOPS Tensor
-
-
-
-
FP64
45.26 TFLOPS
90.52 TFLOPS Tensor
BF16
28.7 TFLOPS
1.84 PFLOPS Tensor
-
BF16
-
362.09 TFLOPS Tensor
-
TF32
458.75 TFLOPS Tensor
-
-
-
-
-
-
-
INT4
362.09 TOPS Tensor
-
-
-
-
-
INT8
-
362.09 TOPS Tensor
-
-
-
-
-
-
-
-
-
Pixel Fillrate
-
Pixel Fillrate
-
-
-
-
-
Texture Fillrate
-
Texture Fillrate
1414.4 GTexel/s
Manufacturer
Intel
Manufacturer
AMD
Chip Designer
Intel
Chip Designer
AMD
Architecture
Gaudi 3
Architecture
CDNA 2
Family
Gaudi
Family
Instinct
Codename
Gaudi 3
Gaudi 3
-
-
Codename
Aldebaran
Aldebaran XT
Variant
Aldebaran XT
Market Segment
Server
Market Segment
Server
Release Date
4/9/2024
Release Date
11/8/2021
Foundry
TSMC
-
Foundry
TSMC
-
Fabrication Node
N5
-
Fabrication Node
N6
-
-
-
-
Die Size
2x 724 mm²
-
-
-
Transistor Count
2x 28 Billion
-
-
-
-
Transistor Density
38.67M/mm²
-
Form
OAM Module
Form
OAM Module
Shading Units
16384 Shaders
-
Shading Units
13312 Shaders
-
Texture Mapping Units
-
Texture Mapping Units
832 TMUs
Render Output Units
-
Render Output Units
-
Tensor Cores
64 T-Cores
Tensor Cores
832 T-Cores
-
-
-
-
-
-
-
-
Compute Units
8 CUs
Compute Units
208 CUs
-
-
-
-
-
-
-
-
-
-
-
438MHz
-
-
1000MHz Base
1700MHz
-
-
-
-
L1
-
-
-
Unknown
L1
-
-
16KB/CU
-
L2
Unknown
L2
16MB Shared
-
-
-
-
-
-
128GB
HBM2e
ECC
128GB
HBM2e
ECC
Bus Width
8192Bit
Bus Width
8192Bit
Clock
1808MHz
Transfer Rate
3.6GT/s
Bandwidth
3702.8GB/s
Clock
1600MHz
Transfer Rate
3.2GT/s
Bandwidth
3276.8GB/s
-
-
-
-
eSRAM
96MB
12800GB/s
-
-
-
-
-
-
-
-
-
-
-
TDP
900W
TDP
500W
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
No Ports
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
No Ports
Max Resolution
Unknown
Max Resolution
Unknown
Max Resolution Refresh Rate
-
Max Resolution Refresh Rate
-
Variable Refresh Rate
-
-
-
Variable Refresh Rate
-
-
-
Display Stream Compression (DSC)
Not Supported
Display Stream Compression (DSC)
Not Supported
Multi Monitor Support
Unknown
Multi Monitor Support
Unknown
-
-
-
-
No Encoders
-
Model
2x VCN 2.6
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
Codec
-
-
-
-
-
-
-
-
AVC (H.264)
HEVC (H.265)
-
-
-
-
No Decoders
No Decoders
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
OpenCL
3.0
-
-
-
-
OpenCL
3.0
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
GFX
9.4
-
-
-
-
Not a Card
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
PCIe Version
5.0
PCIe Lanes
16
-
-
PCIe Version
4.0
PCIe Lanes
16
Multi GPU Support
Supported
Type
RoCE
Multi GPU Support
Supported
Type
Infinity Fabric
-
-
-
-
-
-
-
-
-
-
-
-
Change Comparison