NVIDIA H100 SXM 80GB vs NVIDIA A2

NVIDIA H100 SXM 80GB
NVIDIA A2
16896 Shaders
80GB HBM3
1980MHz
1280 Shaders
16GB GDDR6
1770MHz
Peak AI Performance
3.96 POPS
INT8 Tensor Sparse
Peak AI Performance
145 TOPS
INT4 Tensor Sparse
FP32
66.91 TFLOPS
FP32
4.53 TFLOPS
FP16
133.82 TFLOPS
FP16
4.53 TFLOPS
Form Factor
SXM5
-
Form Factor
PCIe Card
1.0-Slots
TDP
700W
TDP
60W
-
-
-
-
-
-
-
-
-
-
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
3.96 POPS
INT8 Tensor Sparse
Peak AI Performance
145 TOPS
INT4 Tensor Sparse
-
-
-
-
-
-
FP8
-
1.98 PFLOPS Tensor (FP16 Accumulate)
3.96 PFLOPS Tensor (FP16 Accumulate) Sparse
1.98 PFLOPS Tensor (FP32 Accumulate)
3.96 PFLOPS Tensor (FP32 Accumulate) Sparse
-
-
-
-
-
-
FP16
133.82 TFLOPS
989.43 TFLOPS Tensor (FP16 Accumulate)
1.98 PFLOPS Tensor (FP16 Accumulate) Sparse
989.43 TFLOPS Tensor (FP32 Accumulate)
1.98 PFLOPS Tensor (FP32 Accumulate) Sparse
FP16
4.53 TFLOPS
18.13 TFLOPS Tensor (FP16 Accumulate)
36.25 TFLOPS Tensor (FP16 Accumulate) Sparse
18.13 TFLOPS Tensor (FP32 Accumulate)
36.25 TFLOPS Tensor (FP32 Accumulate) Sparse
FP32
66.91 TFLOPS
-
-
FP32
4.53 TFLOPS
-
-
FP64
33.45 TFLOPS
61.84 TFLOPS Tensor
FP64
70 GFLOPS
-
BF16
133.82 TFLOPS
989.43 TFLOPS Tensor
1.98 PFLOPS Tensor Sparse
BF16
4.53 TFLOPS
18.13 TFLOPS Tensor
36.25 TFLOPS Tensor Sparse
TF32
494.72 TFLOPS Tensor
989.43 TFLOPS Tensor Sparse
TF32
9.06 TFLOPS Tensor
18.12 TFLOPS Tensor Sparse
-
-
-
INT4
72.5 TOPS Tensor
145 TOPS Tensor Sparse
INT8
-
1.98 POPS Tensor
3.96 POPS Tensor Sparse
INT8
-
36.25 TOPS Tensor
72.5 TOPS Tensor Sparse
INT32
33.45 TOPS
INT32
2.27 TOPS
-
-
Ray Tracing
8.9 TOPS
Pixel Fillrate
47.52 GPixel/s
Pixel Fillrate
56.64 GPixel/s
-
-
-
-
Texture Fillrate
1045.44 GTexel/s
Texture Fillrate
70.8 GTexel/s
Manufacturer
NVIDIA
Manufacturer
NVIDIA
Chip Designer
NVIDIA
Chip Designer
NVIDIA
Architecture
Hopper
Architecture
Ampere
Family
Server
Family
Server
Codename
NV180
GH100
-
-
Codename
NV177
GA107
-
-
Market Segment
Server
Market Segment
Server
Release Date
3/22/2022
Release Date
11/10/2021
Foundry
TSMC
-
Foundry
Samsung
-
Fabrication Node
4N
-
Fabrication Node
8N
-
Die Size
814 mm²
-
Die Size
200 mm²
-
Transistor Count
80 Billion
-
Transistor Count
8.7 Billion
-
Transistor Density
98.28M/mm²
-
Transistor Density
43.50M/mm²
-
Form
SXM5
Form
PCIe Card
Shading Units
16896 Shaders
-
Shading Units
1280 Shaders
-
Texture Mapping Units
528 TMUs
Texture Mapping Units
40 TMUs
Render Output Units
24 ROPs
Render Output Units
32 ROPs
Tensor Cores
528 T-Cores
Tensor Cores
40 T-Cores
-
-
Ray-Tracing Cores
10 RT-Cores
Streaming Multiprocessors
132 SMs
Streaming Multiprocessors
10 SMs
-
-
-
-
-
-
-
-
-
-
-
-
1830MHz Tensor
-
1065MHz Base
1980MHz
-
-
1440MHz Base
1770MHz
-
-
-
-
L1
64KB/SM Tex
256KB/SM
-
-
L1
64KB/SM Tex
128KB/SM
-
-
L2
50MB Shared
L2
2MB Shared
-
-
-
-
-
-
80GB
HBM3
-
16GB
GDDR6
-
Bus Width
5120Bit
Bus Width
128Bit
Clock
2619MHz
Transfer Rate
5.2GT/s
Bandwidth
3352.3GB/s
Clock
782MHz
Transfer Rate
6.3GT/s
Bandwidth
100GB/s
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
TDP
700W
TDP
60W
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
No Ports
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
No Ports
Max Resolution
Unknown
Max Resolution
Unknown
Max Resolution Refresh Rate
-
Max Resolution Refresh Rate
-
Variable Refresh Rate
G-Sync
FreeSync
-
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
NVENC 7
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
Codec
-
-
-
-
-
-
-
-
AVC (H.264)
HEVC (H.265)
-
-
-
-
Model
7x NVDEC 5
Model
NVDEC 5
Codec
MPEG-1
MPEG-2
MPEG-4
-
VC-1
VP8
VP9
-
AVC (H.264)
HEVC (H.265)
-
AV1
-
-
Codec
MPEG-1
MPEG-2
MPEG-4
-
VC-1
VP8
VP9
-
AVC (H.264)
HEVC (H.265)
-
AV1
-
-
-
-
-
-
Direct X
12
Direct 3D
12_2
-
-
OpenCL
3.0
-
-
OpenGL
4.6
OpenCL
3.0
Vulkan
1.2
-
-
CUDA
9.0
-
-
PureVideo HD
VP11
VDPAU
Feature Set K
Shader Model
6.6
CUDA
8.6
-
-
PureVideo HD
VP11
VDPAU
Feature Set K
Not a Card
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
PCIe Version
5.0
PCIe Lanes
16
Slots Required
1.0
PCIe Version
4.0
PCIe Lanes
8
Multi GPU Support
Supported
Type
NVLink
-
-
-
-
-
-
-
-
-
-
Height
69 mm (2.72 in)
Width
168 mm (6.61 in)
Depth
20 mm (0.79 in)
Change Comparison