AMD Radeon Instinct MI8 vs NVIDIA GRID K1
We compared two Professional market GPUs: 4GB VRAM Radeon Instinct MI8 and 4GB VRAM GRID K1 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
AMD Radeon Instinct MI8 's Advantages
Released 3 years and 9 months late
Larger VRAM bandwidth (512.0GB/s vs 28.51GB/s)
3904 additional rendering cores
NVIDIA GRID K1 's Advantages
Lower TDP (130W vs 175W)
Score
Benchmark
FP32 (float)
Radeon Instinct MI8
+2412%
8.192 TFLOPS
GRID K1
0.326 TFLOPS
Graphics Card
Dec 2016
Release Date
Mar 2013
Radeon Instinct
Generation
GRID
Professional
Type
Professional
PCIe 3.0 x16
Bus Interface
PCIe 3.0 x16
Clock Speeds
-
-
-
-
-
-
500 MHz
Memory Clock
891 MHz
Memory
4GB
Memory Size
4GB
HBM
Memory Type
DDR3
4096bit
Memory Bus
128bit
512.0GB/s
Bandwidth
28.51GB/s
Render Config
64
Compute Units
-
-
-
-
4096
Shading Units
192
256
TMUs
16
64
ROPs
16
-
-
-
-
-
-
16 KB (per CU)
L1 Cache
16 KB (per SMX)
2 MB
L2 Cache
256 KB
-
-
-
Theoretical Performance
64.00 GPixel/s
Pixel Rate
3.400 GPixel/s
256.0 GTexel/s
Texture Rate
13.60 GTexel/s
8.192 TFLOPS
FP16 (half)
-
8.192 TFLOPS
FP32 (float)
326.4 GFLOPS
512.0 GFLOPS
FP64 (double)
13.60 GFLOPS
Board Design
175W
TDP
130W
450 W
Suggested PSU
300 W
No outputs
Outputs
No outputs
1x 8-pin
Power Connectors
1x 6-pin
Graphics Processor
Fiji
GPU Name
GK107
Fiji XT CA
(215-0862120)
GPU Variant
GK107-450-A2
GCN 3.0
Architecture
Kepler
TSMC
Foundry
TSMC
28 nm
Process Size
28 nm
8.9 billion
Transistors
1.27 billion
596 mm²
Die Size
118 mm²
Graphics Features
12 (12_0)
DirectX
12 (11_0)
4.6
OpenGL
4.6
2.1
OpenCL
3.0
1.2.170
Vulkan
1.1
-
CUDA
3.0
6.5
Shader Model
5.1
