Intel Gaudi 3 vs Intel GPU SG-18M 1650MHz
Intel Gaudi 3
Intel GPU SG-18M 1650MHz
|
16384 Shaders
128GB HBM2e
438MHz
|
768 Shaders
Shared Memory
1650MHz
|
|
Peak AI Performance
1.84 PFLOPS
FP8 Tensor (FP32 Accumulate)
|
Peak AI Performance
5.07 TFLOPS
FP16
|
|
FP32
14.35 TFLOPS
|
FP32
2.53 TFLOPS
|
|
FP16
28.7 TFLOPS
|
FP16
5.07 TFLOPS
|
|
Form Factor
OAM Module
-
|
Form Factor
iGPU
-
|
|
TDP
900W
|
TDP
Shared
|
|
-
-
-
-
-
|
-
-
-
-
-
|
|
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
1.84 PFLOPS
FP8 Tensor (FP32 Accumulate)
|
Peak AI
Performance
5.07 TFLOPS
FP16
|
|
-
-
-
|
-
-
-
|
|
FP8
-
-
-
1.84 PFLOPS
Tensor (FP32 Accumulate)
-
|
-
-
-
-
-
-
|
|
FP16
28.7 TFLOPS
-
-
458.75 TFLOPS
Tensor (FP32 Accumulate)
-
|
FP16
5.07 TFLOPS
-
-
-
-
|
|
FP32
14.35 TFLOPS
229.38 TFLOPS
Tensor
-
|
FP32
2.53 TFLOPS
-
-
|
|
-
-
-
|
FP64
630 GFLOPS
-
|
|
BF16
28.7 TFLOPS
1.84 PFLOPS
Tensor
-
|
-
-
-
-
|
|
TF32
458.75 TFLOPS
Tensor
-
|
-
-
-
|
|
-
-
-
|
-
-
-
|
|
-
-
-
-
|
-
-
-
-
|
|
-
-
|
-
-
|
|
-
-
|
-
-
|
|
Pixel
Fillrate
-
|
Pixel
Fillrate
39.6 GPixel/s
|
|
-
-
|
-
-
|
|
Texture
Fillrate
-
|
Texture
Fillrate
79.2 GTexel/s
|
|
Foundry
TSMC
-
|
-
-
-
|
|
Fabrication Node
N5
-
|
-
-
-
|
|
-
-
-
|
-
-
-
|
|
-
-
|
-
-
|
|
-
-
-
|
-
-
-
|
|
Form
OAM Module
|
Form
iGPU
|
|
Shading Units
16384 Shaders
-
|
Shading Units
768 Shaders
-
|
|
Texture Mapping Units
-
|
Texture Mapping Units
48 TMUs
|
|
Render Output Units
-
|
Render Output Units
24 ROPs
|
|
Tensor Cores
64 T-Cores
|
-
-
|
|
-
-
|
-
-
|
|
-
-
|
-
-
|
|
Compute Units
8 CUs
|
-
-
|
|
-
-
|
Execution Units
96 EUs
|
|
-
-
|
-
-
|
|
-
-
-
438MHz
|
-
-
300MHz Base
1650MHz
|
|
-
-
|
-
-
|
|
L1
-
-
-
Unknown
|
L1
-
-
-
Unknown
|
|
L2
Unknown
|
L2
Unknown
|
|
-
-
-
|
-
-
-
|
|
128GB
HBM2e
ECC
|
Shared Memory
-
-
|
|
Bus Width
8192Bit
|
-
|
|
Clock
1808MHz
Transfer Rate
3.6GT/s
Bandwidth
3702.8GB/s
|
-
-
-
-
-
-
|
|
-
-
-
-
eSRAM
96MB
12800GB/s
-
-
|
-
-
-
-
-
-
-
-
-
|
|
TDP
900W
|
TDP
Shared
|
|
-
-
|
-
-
|
|
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
No Ports
|
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
No Ports
|
|
Max Resolution
Unknown
|
Max Resolution
7680x4320
|
|
Max Resolution Refresh Rate
-
|
Max Resolution Refresh Rate
60Hz
|
|
Variable Refresh Rate
-
-
-
|
Variable Refresh Rate
-
-
-
|
|
Display Stream Compression (DSC)
Not Supported
|
Display Stream Compression (DSC)
Supported
|
|
Multi Monitor Support
Unknown
|
Multi Monitor Support
4
|
|
-
-
|
-
-
|
|
No Encoders
-
|
Model
Quick Sync Video 8
|
|
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
|
Codec
-
-
-
JPEG
-
-
VP9
-
AVC (H.264)
HEVC (H.265)
-
AV1
-
-
|
|
No Decoders
|
Model
Quick Sync Video 8
|
|
-
-
-
-
-
-
-
-
-
-
-
-
-
-
|
Codec
MPEG-1
MPEG-2
MPEG-4
JPEG
VC-1
VP8
VP9
-
AVC (H.264)
HEVC (H.265)
-
AV1
-
-
|
|
-
-
-
-
|
Direct X
12
Direct 3D
12_1
|
|
-
-
OpenCL
3.0
-
-
|
OpenGL
4.6
OpenCL
3.0
Vulkan
1.2
|
|
-
-
-
-
-
-
-
-
-
-
|
Shader Model
6.4
-
-
-
-
-
-
-
-
|
|
Not a Card
-
-
-
|
Not a Card
-
-
-
|
|
-
-
-
-
-
-
-
-
|
-
-
-
-
-
-
-
-
|
|
-
-
PCIe Version
5.0
PCIe Lanes
16
|
-
-
-
-
-
-
|
|
Multi GPU Support
Supported
Type
RoCE
|
-
-
-
-
|
|
-
-
-
-
-
-
|
-
-
-
-
-
-
|
Copy Link