AMD Radeon Instinct MI8 vs NVIDIA GRID M40
We compared two Professional market GPUs: 4GB VRAM Radeon Instinct MI8 and 8GB VRAM GRID M40 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
AMD Radeon Instinct MI8 's Advantages
Released 7 months late
Larger VRAM bandwidth (512.0GB/s vs 83.20GB/s)
3712 additional rendering cores
NVIDIA GRID M40 's Advantages
More VRAM (8GB vs 4GB)
Lower TDP (50W vs 175W)
Score
Benchmark
FP32 (float)
Radeon Instinct MI8
+933%
8.192 TFLOPS
GRID M40
0.793 TFLOPS
Graphics Card
Dec 2016
Release Date
May 2016
Radeon Instinct
Generation
GRID
Professional
Type
Professional
PCIe 3.0 x16
Bus Interface
PCIe 3.0 x16
Clock Speeds
-
-
-
-
-
-
500 MHz
Memory Clock
1300 MHz
Memory
4GB
Memory Size
8GB
HBM
Memory Type
GDDR5
4096bit
Memory Bus
128bit
512.0GB/s
Bandwidth
83.20GB/s
Render Config
64
Compute Units
-
-
-
-
4096
Shading Units
384
256
TMUs
32
64
ROPs
16
-
-
-
-
-
-
16 KB (per CU)
L1 Cache
64 KB (per SMM)
2 MB
L2 Cache
2 MB
-
-
-
Theoretical Performance
64.00 GPixel/s
Pixel Rate
16.53 GPixel/s
256.0 GTexel/s
Texture Rate
33.06 GTexel/s
8.192 TFLOPS
FP16 (half)
-
8.192 TFLOPS
FP32 (float)
793.3 GFLOPS
512.0 GFLOPS
FP64 (double)
24.79 GFLOPS
Board Design
175W
TDP
50W
450 W
Suggested PSU
250 W
No outputs
Outputs
No outputs
1x 8-pin
Power Connectors
-
Graphics Processor
Fiji
GPU Name
GM107
Fiji XT CA
(215-0862120)
GPU Variant
-
GCN 3.0
Architecture
Maxwell
TSMC
Foundry
TSMC
28 nm
Process Size
28 nm
8.9 billion
Transistors
1.87 billion
596 mm²
Die Size
148 mm²
Graphics Features
12 (12_0)
DirectX
12 (11_0)
4.6
OpenGL
4.6
2.1
OpenCL
3.0
1.2.170
Vulkan
1.3
-
CUDA
5.0
6.5
Shader Model
5.1
