NVIDIA A100 PCIe 80 GB vs NVIDIA GRID RTX T10 2
We compared two Professional market GPUs: 80GB VRAM A100 PCIe 80 GB and 2GB VRAM GRID RTX T10 2 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA A100 PCIe 80 GB 's Advantages
Released 1 years and 5 months late
Boost Clock has increased by 1% (1410MHz vs 1395MHz)
More VRAM (80GB vs 2GB)
Larger VRAM bandwidth (1.94TB/s vs 672.0GB/s)
3328 additional rendering cores
NVIDIA GRID RTX T10 2 's Advantages
Lower TDP (150W vs 300W)
Score
Benchmark
FP32 (float)
A100 PCIe 80 GB
+94%
19.49 TFLOPS
GRID RTX T10 2
9.999 TFLOPS
Graphics Card
Jun 2021
Release Date
Jan 2020
Tesla Ampere(Axx)
Generation
GRID
Professional
Type
Professional
PCIe 4.0 x16
Bus Interface
PCIe 3.0 x16
Clock Speeds
1065 MHz
Base Clock
1065 MHz
1410 MHz
Boost Clock
1395 MHz
1512 MHz
Memory Clock
1750 MHz
Memory
80GB
Memory Size
2GB
HBM2e
Memory Type
GDDR6
5120bit
Memory Bus
384bit
1.94TB/s
Bandwidth
672.0GB/s
Render Config
-
-
-
108
SM Count
56
6912
Shading Units
3584
432
TMUs
224
160
ROPs
64
432
Tensor Cores
448
-
RT Cores
56
192 KB (per SM)
L1 Cache
64 KB (per SM)
80 MB
L2 Cache
6 MB
-
-
-
Theoretical Performance
225.6 GPixel/s
Pixel Rate
89.28 GPixel/s
609.1 GTexel/s
Texture Rate
312.5 GTexel/s
77.97 TFLOPS
FP16 (half)
20.00 TFLOPS
19.49 TFLOPS
FP32 (float)
9.999 TFLOPS
9.746 TFLOPS
FP64 (double)
312.5 GFLOPS
Board Design
300W
TDP
150W
700 W
Suggested PSU
450 W
No outputs
Outputs
No outputs
8-pin EPS
Power Connectors
1x 6-pin + 1x 8-pin
Graphics Processor
GA100
GPU Name
TU102
-
GPU Variant
TU102-875-A1
Ampere
Architecture
Turing
TSMC
Foundry
TSMC
7 nm
Process Size
12 nm
54.2 billion
Transistors
18.6 billion
826 mm²
Die Size
754 mm²
Graphics Features
N/A
DirectX
12 Ultimate (12_2)
N/A
OpenGL
4.6
3.0
OpenCL
3.0
N/A
Vulkan
1.3
8.0
CUDA
7.5
N/A
Shader Model
6.8
