AMD Radeon Pro V620 vs NVIDIA A100 40GB
AMD Radeon Pro V620
NVIDIA A100 40GB
|
4608 Shaders
32GB GDDR6
2200MHz
|
6912 Shaders
40GB HBM2e
1410MHz
|
|
Peak AI Performance
20.28 TFLOPS
FP32
|
Peak AI Performance
2.49 POPS
INT4 Tensor Sparse
|
|
FP32
20.28 TFLOPS
|
FP32
19.49 TFLOPS
|
|
-
-
|
FP16
77.97 TFLOPS
|
|
Form Factor
PCIe Card
2.0-Slots
|
Form Factor
PCIe Card
2.0-Slots
|
|
TDP
300W
|
TDP
250W
|
|
Power Connectors
2x 8-Pin
|
Power Connectors
-
|
Peak AI Performance
|
|
Radeon Pro V620 - 20.28 TFLOPS FP32
x1
A100 40GB - 2.49 POPS INT4 Tensor Sparse
x122.78
FP32
|
|
Radeon Pro V620 - 20.28 TFLOPS FP32
x1.04
A100 40GB - 19.49 TFLOPS FP32
x1
|
|
Radeon Pro V620 - 512GB/s
x1
A100 40GB - 1555.2GB/s
x3.04
|
|
Radeon Pro V620 - 300W
x1.2
A100 40GB - 250W
x1
|
|
Radeon Pro V620 - GB6 OpenCL 33,755
x1
A100 40GB - GB6 OpenCL 199,845
x5.92
|
0%
|
0%
|
|
0%
|
0%
|
|
0%
|
0%
|
|
0%
|
0%
|
|
0%
|
0%
|
|
0%
|
0%
|
|
0%
|
0%
|
|
Manufacturer
AMD
|
Manufacturer
NVIDIA
|
|
Chip Designer
AMD
|
Chip Designer
NVIDIA
|
|
Architecture
RDNA 2
|
Architecture
Ampere
|
|
Family
Radeon Pro V
|
Family
Server
|
|
Codename
Sienna Cichlid
Navi 21
Variant
Navi 21 XL GL
|
Codename
NV170
GA100
-
-
|
|
Market Segment
Server
|
Market Segment
Server
|
|
Release Date
11/4/2021
|
Release Date
6/28/2021
|
|
Foundry
TSMC
|
Foundry
TSMC
|
|
Fabrication Node
N7
|
Fabrication Node
7N
|
|
Die Size
520 mm²
|
Die Size
826 mm²
|
|
Transistor Count
26.8 Billion
|
Transistor Count
54.2 Billion
|
|
Transistor Density
51.56M/mm²
|
Transistor Density
65.62M/mm²
|
|
Form
PCIe Card
|
Form
PCIe Card
|
|
Shading Units
4608 Shaders
|
Shading Units
6912 Shaders
|
|
Texture Mapping Units
288 TMUs
|
Texture Mapping Units
432 TMUs
|
|
Render Output Units
128 ROPs
|
Render Output Units
160 ROPs
|
|
-
-
|
Tensor Cores
432 T-Cores
|
|
-
-
|
Streaming Multiprocessors
108 SMs
|
|
Compute Units
72 CUs
|
-
-
|
|
1825MHz Base
2200MHz
|
765MHz Base
1410MHz
|
|
Peak AI Performance
20.28 TFLOPS
FP32
|
Peak AI Performance
2.49 POPS
INT4 Tensor Sparse
|
|
-
-
-
-
-
-
|
FP16
77.97 TFLOPS
311.87 TFLOPS Tensor (FP16 Accumulate)
623.74 TFLOPS Tensor (FP16 Accumulate) Sparse
311.87 TFLOPS Tensor (FP32 Accumulate)
623.74 TFLOPS Tensor (FP32 Accumulate) Sparse
|
|
FP32
20.28 TFLOPS
|
FP32
19.49 TFLOPS
|
|
FP64
1.27 TFLOPS
-
|
FP64
9.75 TFLOPS
19.49 TFLOPS Tensor
|
|
-
-
-
-
|
BF16
38.98 TFLOPS
311.87 TFLOPS Tensor
623.74 TFLOPS Tensor Sparse
|
|
-
-
-
|
TF32
155.94 TFLOPS Tensor
311.87 TFLOPS Tensor Sparse
|
|
-
-
-
|
INT4
1.25 POPS Tensor
2.49 POPS Tensor Sparse
|
|
-
-
-
|
INT8
623.74 TOPS Tensor
1.25 POPS Tensor Sparse
|
|
-
-
|
INT32
19.49 TOPS
|
|
Pixel Fillrate
281.6 GPixel/s
|
Pixel Fillrate
225.6 GPixel/s
|
|
Texture Fillrate
633.6 GTexel/s
|
Texture Fillrate
609.12 GTexel/s
|
|
L0
32KB/WGP
|
-
-
|
|
L1
-
-
128KB/Array
|
L1
64KB/SM Tex
192KB/SM
-
|
|
L2
4MB Shared
|
L2
40MB Shared
|
|
L3
128MB Shared
1.66TB/s
|
-
-
-
|
|
32GB
GDDR6
|
40GB
HBM2e
|
|
Bus Width
256Bit
|
Bus Width
5120Bit
|
|
Clock
2000MHz
Transfer Rate
16GT/s
Bandwidth
512GB/s
|
Clock
1215MHz
Transfer Rate
2.4GT/s
Bandwidth
1555.2GB/s
|
|
TDP
300W
|
TDP
250W
|
|
Max Resolution
7680x4320
|
Max Resolution
Unknown
|
|
Max Resolution Refresh Rate
120Hz
|
Max Resolution Refresh Rate
-
|
|
Variable Refresh Rate
-
FreeSync
|
Variable Refresh Rate
G-Sync
FreeSync
|
|
Display Stream Compression (DSC)
Supported
|
Display Stream Compression (DSC)
Not Supported
|
|
Multi Monitor Support
4
|
Multi Monitor Support
Unknown
|
|
Content Protection
HDCP 2.3
|
-
-
|
|
Model
VCN 3.0
|
No Encoders
-
|
|
Codec
AVC (H.264)
HEVC (H.265)
|
-
-
-
|
|
Model
VCN 3.0
|
Model
5x NVDEC 4
|
|
Codec
MPEG-1
MPEG-2
MPEG-4
JPEG
VC-1
-
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)
-
|
|
Direct X
12
Direct 3D
12_2
|
-
-
-
-
|
|
OpenGL
4.6
OpenCL
2.1
Vulkan
1.2
|
-
-
OpenCL
3.0
Vulkan
1.2
|
|
Shader Model
6.7
-
-
GFX
10.3
-
-
-
-
|
-
-
CUDA
8.0
-
-
PureVideo HD
VP10
VDPAU
Feature Set J
|
|
Power Connectors
2x 8-Pin
-
|
Power Connectors
-
1x 8-Pin EPS
|
|
Slots Required
2.0
PCIe Version
4.0
PCIe Lanes
16
|
Slots Required
2.0
PCIe Version
4.0
PCIe Lanes
16
|
|
Multi GPU Support
Supported
Type
CrossFire XDMA
|
Multi GPU Support
Supported
Type
NVLink
|
|
Height
111 mm (4.37 in)
Width
267 mm (10.51 in)
Depth
37 mm (1.46 in)
|
Height
111 mm (4.37 in)
Width
267 mm (10.51 in)
Depth
40 mm (1.57 in)
|
Copy Link