NVIDIA Tesla S1070 vs AMD Radeon Instinct MI8
We compared two Professional market GPUs: 4GB VRAM Tesla S1070 and 4GB VRAM Radeon Instinct MI8 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
AMD Radeon Instinct MI8 's Advantages
Released 8 years and 6 months late
Larger VRAM bandwidth (512.0GB/s vs 102.4GB/s)
3856 additional rendering cores
Lower TDP (175W vs 800W)
Score
Benchmark
FP32 (float)
Tesla S1070
0.622 TFLOPS
Radeon Instinct MI8
+1217%
8.192 TFLOPS
Graphics Card
Jun 2008
Release Date
Dec 2016
Tesla
Generation
Radeon Instinct
Professional
Type
Professional
PCIe 2.0 x16
Bus Interface
PCIe 3.0 x16
Clock Speeds
-
-
-
-
-
-
800 MHz
Memory Clock
500 MHz
Memory
4GB
Memory Size
4GB
GDDR3
Memory Type
HBM
512bit
Memory Bus
4096bit
102.4GB/s
Bandwidth
512.0GB/s
Render Config
-
Compute Units
64
30
SM Count
-
240
Shading Units
4096
80
TMUs
256
32
ROPs
64
-
-
-
-
-
-
-
L1 Cache
16 KB (per CU)
256 KB
L2 Cache
2 MB
-
-
-
Theoretical Performance
19.52 GPixel/s
Pixel Rate
64.00 GPixel/s
48.80 GTexel/s
Texture Rate
256.0 GTexel/s
-
FP16 (half)
8.192 TFLOPS
622.1 GFLOPS
FP32 (float)
8.192 TFLOPS
77.76 GFLOPS
FP64 (double)
512.0 GFLOPS
Board Design
800W
TDP
175W
1200 W
Suggested PSU
450 W
No outputs
Outputs
No outputs
-
Power Connectors
1x 8-pin
Graphics Processor
GT200B
GPU Name
Fiji
-
GPU Variant
Fiji XT CA
(215-0862120)
Tesla 2.0
Architecture
GCN 3.0
TSMC
Foundry
TSMC
55 nm
Process Size
28 nm
1.4 billion
Transistors
8.9 billion
470 mm²
Die Size
596 mm²
Graphics Features
11.1 (10_0)
DirectX
12 (12_0)
3.3
OpenGL
4.6
1.1
OpenCL
2.1
N/A
Vulkan
1.2.170
1.3
CUDA
-
4.0
Shader Model
6.5
