Intel Gaudi 3 vs NVIDIA Tesla P100 SXM

Intel Gaudi 3
NVIDIA Tesla P100 SXM
16384 Shaders
128GB HBM2e
438MHz
3584 Shaders
16GB HBM2
1480MHz
Peak AI Performance
1.84 PFLOPS
FP8 Tensor (FP32 Accumulate)
Peak AI Performance
21.22 TFLOPS
FP16
FP32
14.35 TFLOPS
FP32
10.61 TFLOPS
FP16
28.7 TFLOPS
FP16
21.22 TFLOPS
Form Factor
OAM Module
-
Form Factor
SXM
-
TDP
900W
TDP
300W
-
-
-
-
-
-
-
-
-
-
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
21.22 TFLOPS
FP16
-
-
-
-
-
-
FP8
-
-
-
1.84 PFLOPS Tensor (FP32 Accumulate)
-
-
-
-
-
-
-
FP16
28.7 TFLOPS
-
-
458.75 TFLOPS Tensor (FP32 Accumulate)
-
FP16
21.22 TFLOPS
-
-
-
-
FP32
14.35 TFLOPS
229.38 TFLOPS Tensor
-
FP32
10.61 TFLOPS
-
-
-
-
-
FP64
5.3 TFLOPS
-
BF16
28.7 TFLOPS
1.84 PFLOPS Tensor
-
-
-
-
-
TF32
458.75 TFLOPS Tensor
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
Pixel Fillrate
-
Pixel Fillrate
189.44 GPixel/s
-
-
-
-
Texture Fillrate
-
Texture Fillrate
331.52 GTexel/s
Manufacturer
Intel
Manufacturer
NVIDIA
Chip Designer
Intel
Chip Designer
NVIDIA
Architecture
Gaudi 3
Architecture
Pascal
Family
Gaudi
Family
Tesla P
Codename
Gaudi 3
Gaudi 3
-
-
Codename
NV130
GP100
Variant
GP100-890-A1
Market Segment
Server
Market Segment
Server
Release Date
4/9/2024
Release Date
4/5/2016
Foundry
TSMC
-
Foundry
TSMC
-
Fabrication Node
N5
-
Fabrication Node
16FF
-
-
-
-
Die Size
610 mm²
-
-
-
Transistor Count
15.3 Billion
-
-
-
-
Transistor Density
25.08M/mm²
-
Form
OAM Module
Form
SXM
Shading Units
16384 Shaders
-
Shading Units
3584 Shaders
-
Texture Mapping Units
-
Texture Mapping Units
224 TMUs
Render Output Units
-
Render Output Units
128 ROPs
Tensor Cores
64 T-Cores
-
-
-
-
-
-
-
-
Streaming Multiprocessors
56 SMs
Compute Units
8 CUs
-
-
-
-
-
-
-
-
-
-
-
-
-
438MHz
-
-
1328MHz Base
1480MHz
-
-
-
-
L1
-
-
-
Unknown
L1
-
64KB/SM
-
-
L2
Unknown
L2
4MB Shared
-
-
-
-
-
-
128GB
HBM2e
ECC
16GB
HBM2
-
Bus Width
8192Bit
Bus Width
4096Bit
Clock
1808MHz
Transfer Rate
3.6GT/s
Bandwidth
3702.8GB/s
Clock
715MHz
Transfer Rate
1.4GT/s
Bandwidth
732.2GB/s
-
-
-
-
eSRAM
96MB
12800GB/s
-
-
-
-
-
-
-
-
-
-
-
TDP
900W
TDP
300W
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
No Ports
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
No Ports
Max Resolution
Unknown
Max Resolution
Unknown
Max Resolution Refresh Rate
-
Max Resolution Refresh Rate
-
Variable Refresh Rate
-
-
-
Variable Refresh Rate
G-Sync
FreeSync
-
Display Stream Compression (DSC)
Not Supported
Display Stream Compression (DSC)
Not Supported
Multi Monitor Support
Unknown
Multi Monitor Support
Unknown
-
-
-
-
No Encoders
-
Model
3x NVENC 4
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
Codec
-
-
-
-
-
-
-
-
AVC (H.264)
HEVC (H.265)
-
-
-
-
No Decoders
Model
NVDEC 3
-
-
-
-
-
-
-
-
-
-
-
-
-
-
Codec
MPEG-1
MPEG-2
MPEG-4
-
VC-1
-
VP9
-
AVC (H.264)
HEVC (H.265)
-
-
-
-
-
-
-
-
Direct X
12
Direct 3D
12_1
-
-
OpenCL
3.0
-
-
OpenGL
4.6
OpenCL
3.0
Vulkan
1.3
-
-
-
-
-
-
-
-
-
-
Shader Model
6.0
CUDA
6.0
-
-
PureVideo HD
VP8
VDPAU
Feature Set H
Not a Card
-
-
-
Not a Card
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
PCIe Version
5.0
PCIe Lanes
16
-
-
PCIe Version
3.0
PCIe Lanes
16
Multi GPU Support
Supported
Type
RoCE
Multi GPU Support
Supported
-
-
-
-
-
-
-
-
-
-
-
-
-
-
Change Comparison