NVIDIA GRID A100B vs NVIDIA Tesla C2090
We compared two Professional market GPUs: 48GB VRAM GRID A100B and 6GB VRAM Tesla C2090 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA GRID A100B 's Advantages
Released 8 years and 10 months late
Boost Clock1005MHz
More VRAM (48GB vs 6GB)
Larger VRAM bandwidth (1866GB/s vs 177.4GB/s)
6400 additional rendering cores
NVIDIA Tesla C2090 's Advantages
Lower TDP (250W vs 400W)
Score
Benchmark
FP32 (float)
GRID A100B
+942%
13.89 TFLOPS
Tesla C2090
1.332 TFLOPS
Graphics Card
May 2020
Release Date
Jul 2011
GRID
Generation
Tesla
Professional
Type
Professional
PCIe 4.0 x16
Bus Interface
PCIe 2.0 x16
Clock Speeds
900 MHz
Base Clock
-
1005 MHz
Boost Clock
-
1215 MHz
Memory Clock
924 MHz
Memory
48GB
Memory Size
6GB
HBM2e
Memory Type
GDDR5
6144bit
Memory Bus
384bit
1866GB/s
Bandwidth
177.4GB/s
Render Config
-
-
-
108
SM Count
16
6912
Shading Units
512
432
TMUs
64
192
ROPs
48
432
Tensor Cores
-
-
-
-
192 KB (per SM)
L1 Cache
64 KB (per SM)
48 MB
L2 Cache
768 KB
-
-
-
Theoretical Performance
193.0 GPixel/s
Pixel Rate
20.83 GPixel/s
434.2 GTexel/s
Texture Rate
41.66 GTexel/s
55.57 TFLOPS
FP16 (half)
-
13.89 TFLOPS
FP32 (float)
1332 GFLOPS
6.947 TFLOPS
FP64 (double)
666.1 GFLOPS
Board Design
400W
TDP
250W
800 W
Suggested PSU
600 W
No outputs
Outputs
No outputs
None
Power Connectors
-
Graphics Processor
GA100
GPU Name
GF110
-
-
-
Ampere
Architecture
Fermi 2.0
TSMC
Foundry
TSMC
7 nm
Process Size
40 nm
54.2 billion
Transistors
3 billion
826 mm²
Die Size
520 mm²
Graphics Features
N/A
DirectX
12 (11_0)
N/A
OpenGL
4.6
3.0
OpenCL
1.1
N/A
Vulkan
N/A
8.0
CUDA
2.0
N/A
Shader Model
5.1
