AMD Instinct MI300P vs Intel Gaudi

AMD Instinct MI300P
Intel Gaudi
9728 Shaders
64GB HBM3
2100MHz
2048 Shaders
32GB HBM2
610MHz
Peak AI Performance
2.61 POPS
INT4 Tensor Sparse
Peak AI Performance
159.91 TFLOPS
BF16 Tensor
FP32
81.72 TFLOPS
-
-
FP16
81.72 TFLOPS
-
-
Form Factor
OAM Module
-
Form Factor
OAM Module
-
TDP
300W
TDP
350W
-
-
-
-
-
-
-
-
-
-
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
2.61 POPS
INT4 Tensor Sparse
Peak AI Performance
159.91 TFLOPS
BF16 Tensor
-
-
-
-
-
-
FP8
-
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
81.72 TFLOPS
653.72 TFLOPS Tensor (FP16 Accumulate)
1.31 PFLOPS Tensor (FP16 Accumulate) Sparse
653.72 TFLOPS Tensor (FP32 Accumulate)
1.31 PFLOPS Tensor (FP32 Accumulate) Sparse
-
-
-
-
-
-
FP32
81.72 TFLOPS
81.72 TFLOPS Tensor
163.43 TFLOPS Tensor Sparse
-
-
-
-
FP64
40.86 TFLOPS
81.72 TFLOPS Tensor
-
-
-
BF16
-
653.72 TFLOPS Tensor
1.31 PFLOPS Tensor Sparse
BF16
-
159.91 TFLOPS Tensor
-
TF32
326.86 TFLOPS Tensor
653.72 TFLOPS Tensor Sparse
-
-
-
INT4
1.31 POPS Tensor
2.61 POPS Tensor Sparse
-
-
-
INT8
-
1.31 POPS Tensor
2.61 POPS Tensor Sparse
-
-
-
-
-
-
-
-
-
-
-
-
Pixel Fillrate
-
Pixel Fillrate
-
-
-
-
-
Texture Fillrate
1276.8 GTexel/s
Texture Fillrate
-
Manufacturer
AMD
Manufacturer
Intel
Chip Designer
AMD
Chip Designer
Intel
Architecture
CDNA 3
Architecture
Gaudi
Family
Instinct
Family
Gaudi
Codename
Aqua Vanjaram
Aqua Vanjaram XL
Variant
Aqua Vanjaram XL
Codename
Gaudi
HL-2000
Variant
HL-2000
Market Segment
Server
Market Segment
Server
Release Date
12/6/2023
Release Date
6/17/2019
Foundry
TSMC
TSMC Active Interposer Die
Foundry
TSMC
-
Fabrication Node
N5
N6 Active Interposer Die
Fabrication Node
16FF
-
Die Size
2x 370 mm²
-
-
-
-
Transistor Count
2x 36.5 Billion
-
-
-
Transistor Density
98.65M/mm²
-
-
-
-
Form
OAM Module
Form
OAM Module
Shading Units
9728 Shaders
-
Shading Units
2048 Shaders
-
Texture Mapping Units
608 TMUs
Texture Mapping Units
-
Render Output Units
-
Render Output Units
-
Tensor Cores
608 T-Cores
Tensor Cores
8 T-Cores
-
-
-
-
-
-
-
-
Compute Units
152 CUs
Compute Units
1 CU
-
-
-
-
-
-
-
-
-
-
1000MHz Base
2100MHz
-
-
-
610MHz
-
-
-
-
L1
-
-
16KB/CU
-
L1
-
-
-
Unknown
L2
16MB Shared
L2
Unknown
L3
128MB Shared
-
-
-
-
64GB
HBM3
ECC
32GB
HBM2
ECC
Bus Width
4096Bit
Bus Width
4096Bit
Clock
2600MHz
Transfer Rate
5.2GT/s
Bandwidth
2662.4GB/s
Clock
980MHz
Transfer Rate
2GT/s
Bandwidth
1003.5GB/s
-
-
-
-
-
-
-
-
-
-
-
-
-
eSRAM
24MB
3200GB/s
-
-
TDP
300W
TDP
350W
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
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
-
-
-
-
-
-
-
-
-
-
-
-
Change Comparison