AMD Instinct MI325X vs Intel Gaudi 2
AMD Instinct MI325X
Intel Gaudi 2
|
19456 Shaders
288GB HBM3e
2100MHz
|
6144 Shaders
96GB HBM2e
550MHz
|
|
Peak AI Performance
5.23 POPS
INT4 Tensor Sparse
|
Peak AI Performance
865.08 TFLOPS
FP8 Tensor (FP32 Accumulate)
|
|
FP32
163.43 TFLOPS
|
FP32
5.5 TFLOPS
|
|
FP16
163.43 TFLOPS
|
FP16
11 TFLOPS
|
|
Form Factor
OAM Module
-
|
Form Factor
OAM Module
-
|
|
TDP
560W
|
TDP
600W
|
|
-
-
-
-
-
|
-
-
-
-
-
|
|
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
5.23 POPS
INT4 Tensor Sparse
|
Peak AI
Performance
865.08 TFLOPS
FP8 Tensor (FP32 Accumulate)
|
|
-
-
-
|
-
-
-
|
|
FP8
-
2.61 PFLOPS
Tensor (FP16 Accumulate)
5.23 PFLOPS
Tensor (FP16 Accumulate) Sparse
2.61 PFLOPS
Tensor (FP32 Accumulate)
5.23 PFLOPS
Tensor (FP32 Accumulate) Sparse
|
FP8
-
-
-
865.08 TFLOPS
Tensor (FP32 Accumulate)
-
|
|
FP16
163.43 TFLOPS
1.31 PFLOPS
Tensor (FP16 Accumulate)
2.61 PFLOPS
Tensor (FP16 Accumulate) Sparse
1.31 PFLOPS
Tensor (FP32 Accumulate)
2.61 PFLOPS
Tensor (FP32 Accumulate) Sparse
|
FP16
11 TFLOPS
-
-
-
-
|
|
FP32
163.43 TFLOPS
163.43 TFLOPS
Tensor
326.86 TFLOPS
Tensor Sparse
|
FP32
5.5 TFLOPS
-
-
|
|
FP64
81.72 TFLOPS
163.43 TFLOPS
Tensor
|
-
-
-
|
|
BF16
-
1.31 PFLOPS
Tensor
2.61 PFLOPS
Tensor Sparse
|
BF16
11 TFLOPS
432.54 TFLOPS
Tensor
-
|
|
TF32
653.72 TFLOPS
Tensor
1.31 PFLOPS
Tensor Sparse
|
-
-
-
|
|
INT4
2.61 POPS
Tensor
5.23 POPS
Tensor Sparse
|
-
-
-
|
|
INT8
-
2.61 POPS
Tensor
5.23 POPS
Tensor Sparse
|
-
-
-
-
|
|
-
-
|
-
-
|
|
-
-
|
-
-
|
|
Pixel
Fillrate
-
|
Pixel
Fillrate
-
|
|
-
-
|
-
-
|
|
Texture
Fillrate
2553.6 GTexel/s
|
Texture
Fillrate
-
|
|
Manufacturer
AMD
|
Manufacturer
Intel
|
|
Chip Designer
AMD
|
Chip Designer
Intel
|
|
Architecture
CDNA 3
|
Architecture
Gaudi 2
|
|
Family
Instinct
|
Family
Gaudi
|
|
Codename
Aqua Vanjaram
Aqua Vanjaram XTX
Variant
Aqua Vanjaram XTX
|
Codename
Gaudi 2
HL-2080
Variant
HL-2080
|
|
Market Segment
Server
|
Market Segment
Server
|
|
Release Date
6/2/2024
|
Release Date
5/1/2022
|
|
Foundry
TSMC
TSMC Active Interposer Die
|
Foundry
TSMC
-
|
|
Fabrication Node
N5
N6 Active Interposer Die
|
Fabrication Node
N7
-
|
|
Die Size
4x 370 mm²
-
|
-
-
-
|
|
Transistor Count
4x 36.5 Billion
-
|
-
-
|
|
Transistor Density
98.65M/mm²
-
|
-
-
-
|
|
Form
OAM Module
|
Form
OAM Module
|
|
Shading Units
19456 Shaders
-
|
Shading Units
6144 Shaders
-
|
|
Texture Mapping Units
1216 TMUs
|
Texture Mapping Units
-
|
|
Render Output Units
-
|
Render Output Units
-
|
|
Tensor Cores
1216 T-Cores
|
Tensor Cores
24 T-Cores
|
|
-
-
|
-
-
|
|
-
-
|
-
-
|
|
Compute Units
304 CUs
|
Compute Units
2 CUs
|
|
-
-
|
-
-
|
|
-
-
|
-
-
|
|
-
-
1000MHz Base
2100MHz
|
-
-
-
550MHz
|
|
-
-
|
-
-
|
|
L1
-
-
16KB/CU
-
|
L1
-
-
-
Unknown
|
|
L2
16MB Shared
|
L2
Unknown
|
|
L3
256MB Shared
-
|
-
-
-
|
|
288GB
HBM3e
ECC
|
96GB
HBM2e
ECC
|
|
Bus Width
8192Bit
|
Bus Width
6144Bit
|
|
Clock
2933MHz
Transfer Rate
5.9GT/s
Bandwidth
6006.8GB/s
|
Clock
1596MHz
Transfer Rate
3.2GT/s
Bandwidth
2451.5GB/s
|
|
-
-
-
-
-
-
-
-
-
|
-
-
-
-
eSRAM
48MB
6400GB/s
-
-
|
|
TDP
560W
|
TDP
600W
|
|
-
-
|
-
-
|
|
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
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
|
|
-
-
|
-
-
|
|
Model
2x VCN 2.6
|
No Encoders
-
|
|
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
Infinity Fabric
|
Multi GPU Support
Supported
Type
RoCE
|
|
-
-
-
-
-
-
|
-
-
-
-
-
-
|
Copy Link