Radeon Instinct MI250 vs Tesla C2070
We compared two Professional market GPUs: 128GB VRAM Radeon Instinct MI250 and 6GB VRAM Tesla C2070 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
Radeon Instinct MI250 's Advantages
Released 10 years and 4 months late
Boost Clock1700MHz
More VRAM (128GB vs 6GB)
Larger VRAM bandwidth (3277GB/s vs 143.4GB/s)
12864 additional rendering cores
Tesla C2070 's Advantages
Lower TDP (238W vs 500W)
Score
Benchmark
FP32 (float)
Radeon Instinct MI250
+4302%
45260
Tesla C2070
1028
Graphics Card
Nov 2021
Release Date
Jul 2011
Radeon Instinct
Generation
Tesla
Professional
Type
Professional
PCIe 4.0 x16
Bus Interface
PCIe 2.0 x16
Clock Speeds
1000 MHz
Base Clock
-
1700 MHz
Boost Clock
-
1600 MHz
Memory Clock
747 MHz
Memory
128GB
Memory Size
6GB
HBM2e
Memory Type
GDDR5
8192bit
Memory Bus
384bit
3277GB/s
Bandwidth
143.4GB/s
Render Config
208
Compute Units
-
-
SM Count
14
13312
Shading Units
448
832
TMUs
56
0
ROPs
48
16 KB (per CU)
L1 Cache
64 KB (per SM)
16 MB
L2 Cache
768 KB
Theoretical Performance
0 MPixel/s
Pixel Rate
16.07 GPixel/s
1414 GTexel/s
Texture Rate
32.14 GTexel/s
362.1 TFLOPS
FP16 (half)
-
45.26 TFLOPS
FP32 (float)
1028 GFLOPS
45.26 TFLOPS
FP64 (double)
513.9 GFLOPS
Board Design
500W
TDP
238W
900 W
Suggested PSU
550 W
No outputs
Outputs
1x DVI
2x 8-pin
Power Connectors
1x 8-pin
Graphics Processor
Aldebaran
GPU Name
GF100
Aldebaran
GPU Variant
-
CDNA 2.0
Architecture
Fermi
TSMC
Foundry
TSMC
6 nm
Process Size
40 nm
58.2 billion
Transistors
3.1 billion
Unknown
Die Size
529 mm²
Graphics Features
N/A
DirectX
12 (11_0)
N/A
OpenGL
4.6
3.0
OpenCL
1.1
N/A
Vulkan
N/A
-
CUDA
2.0
N/A
Shader Model
5.1
