AMD Radeon Instinct MI8 vs NVIDIA Tesla M6
We compared two Professional market GPUs: 4GB VRAM Radeon Instinct MI8 and 8GB VRAM Tesla M6 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
AMD Radeon Instinct MI8 's Advantages
Released 1 years and 4 months late
Larger VRAM bandwidth (512.0GB/s vs 160.4GB/s)
2560 additional rendering cores
NVIDIA Tesla M6 's Advantages
Boost Clock1180MHz
More VRAM (8GB vs 4GB)
Lower TDP (100W vs 175W)
Score
Benchmark
FP32 (float)
Radeon Instinct MI8
+125%
8.192 TFLOPS
Tesla M6
3.625 TFLOPS
Graphics Card
Dec 2016
Release Date
Aug 2015
Radeon Instinct
Generation
Tesla
Professional
Type
Professional
PCIe 3.0 x16
Bus Interface
PCIe 3.0 x16
Clock Speeds
-
Base Clock
930 MHz
-
Boost Clock
1180 MHz
500 MHz
Memory Clock
1253 MHz
Memory
4GB
Memory Size
8GB
HBM
Memory Type
GDDR5
4096bit
Memory Bus
256bit
512.0GB/s
Bandwidth
160.4GB/s
Render Config
64
Compute Units
-
-
-
-
4096
Shading Units
1536
256
TMUs
96
64
ROPs
64
-
-
-
-
-
-
16 KB (per CU)
L1 Cache
48 KB (per SMM)
2 MB
L2 Cache
2 MB
-
-
-
Theoretical Performance
64.00 GPixel/s
Pixel Rate
75.52 GPixel/s
256.0 GTexel/s
Texture Rate
113.3 GTexel/s
8.192 TFLOPS
FP16 (half)
-
8.192 TFLOPS
FP32 (float)
3.625 TFLOPS
512.0 GFLOPS
FP64 (double)
113.3 GFLOPS
Board Design
175W
TDP
100W
450 W
Suggested PSU
300 W
No outputs
Outputs
No outputs
1x 8-pin
Power Connectors
None
Graphics Processor
Fiji
GPU Name
GM204
Fiji XT CA
(215-0862120)
GPU Variant
GM204-995-A1
GCN 3.0
Architecture
Maxwell 2.0
TSMC
Foundry
TSMC
28 nm
Process Size
28 nm
8.9 billion
Transistors
5.2 billion
596 mm²
Die Size
398 mm²
Graphics Features
12 (12_0)
DirectX
12 (12_1)
4.6
OpenGL
4.6
2.1
OpenCL
3.0
1.2.170
Vulkan
1.3
-
CUDA
5.2
6.5
Shader Model
6.4
