NVIDIA GRID A100B vs NVIDIA Tesla K40st
We compared two Professional market GPUs: 48GB VRAM GRID A100B and 12GB VRAM Tesla K40st to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA GRID A100B 's Advantages
Released 6 years and 6 months late
Boost Clock1005MHz
More VRAM (48GB vs 12GB)
Larger VRAM bandwidth (1866GB/s vs 288.4GB/s)
4032 additional rendering cores
NVIDIA Tesla K40st 's Advantages
Lower TDP (245W vs 400W)
Score
Benchmark
FP32 (float)
GRID A100B
+319%
13.89 TFLOPS
Tesla K40st
3.312 TFLOPS
Graphics Card
May 2020
Release Date
Nov 2013
GRID
Generation
Tesla
Professional
Type
Professional
PCIe 4.0 x16
Bus Interface
PCIe 3.0 x16
Clock Speeds
900 MHz
Base Clock
-
1005 MHz
Boost Clock
-
1215 MHz
Memory Clock
1502 MHz
Memory
48GB
Memory Size
12GB
HBM2e
Memory Type
GDDR5
6144bit
Memory Bus
384bit
1866GB/s
Bandwidth
288.4GB/s
Render Config
-
-
-
108
SM Count
-
6912
Shading Units
2880
432
TMUs
240
192
ROPs
48
432
Tensor Cores
-
-
-
-
192 KB (per SM)
L1 Cache
16 KB (per SMX)
48 MB
L2 Cache
1536 KB
-
-
-
Theoretical Performance
193.0 GPixel/s
Pixel Rate
34.50 GPixel/s
434.2 GTexel/s
Texture Rate
138.0 GTexel/s
55.57 TFLOPS
FP16 (half)
-
13.89 TFLOPS
FP32 (float)
3.312 TFLOPS
6.947 TFLOPS
FP64 (double)
1104 GFLOPS
Board Design
400W
TDP
245W
800 W
Suggested PSU
550 W
No outputs
Outputs
No outputs
None
Power Connectors
-
Graphics Processor
GA100
GPU Name
GK110B
-
-
-
Ampere
Architecture
Kepler
TSMC
Foundry
TSMC
7 nm
Process Size
28 nm
54.2 billion
Transistors
7.08 billion
826 mm²
Die Size
561 mm²
Graphics Features
N/A
DirectX
12 (11_1)
N/A
OpenGL
4.6
3.0
OpenCL
3.0
N/A
Vulkan
1.1
8.0
CUDA
3.5
N/A
Shader Model
5.1
