AMD Radeon Instinct MI8 vs NVIDIA Quadro CX
We compared two Professional market GPUs: 4GB VRAM Radeon Instinct MI8 and 1536MB VRAM Quadro CX 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 1 months late
More VRAM (4GB vs 1536GB)
Larger VRAM bandwidth (512.0GB/s vs 76.80GB/s)
3904 additional rendering cores
NVIDIA Quadro CX 's Advantages
Lower TDP (150W vs 175W)
Score
Benchmark
FP32 (float)
Radeon Instinct MI8
+1673%
8.192 TFLOPS
Quadro CX
0.462 TFLOPS
Graphics Card
Dec 2016
Release Date
Nov 2008
Radeon Instinct
Generation
Quadro CX
Professional
Type
Professional
PCIe 3.0 x16
Bus Interface
PCIe 2.0 x16
Clock Speeds
-
-
-
-
-
-
500 MHz
Memory Clock
800 MHz
Memory
4GB
Memory Size
1536MB
HBM
Memory Type
GDDR3
4096bit
Memory Bus
384bit
512.0GB/s
Bandwidth
76.80GB/s
Render Config
64
Compute Units
-
-
SM Count
24
4096
Shading Units
192
256
TMUs
64
64
ROPs
24
-
-
-
-
-
-
16 KB (per CU)
L1 Cache
-
2 MB
L2 Cache
192 KB
-
-
-
Theoretical Performance
64.00 GPixel/s
Pixel Rate
14.45 GPixel/s
256.0 GTexel/s
Texture Rate
38.53 GTexel/s
8.192 TFLOPS
FP16 (half)
-
8.192 TFLOPS
FP32 (float)
462.3 GFLOPS
512.0 GFLOPS
FP64 (double)
57.79 GFLOPS
Board Design
175W
TDP
150W
450 W
Suggested PSU
450 W
No outputs
Outputs
1x DVI
2x DisplayPort
1x S-Video
1x 8-pin
Power Connectors
1x 6-pin
Graphics Processor
Fiji
GPU Name
GT200B
Fiji XT CA
(215-0862120)
GPU Variant
-
GCN 3.0
Architecture
Tesla 2.0
TSMC
Foundry
TSMC
28 nm
Process Size
55 nm
8.9 billion
Transistors
1.4 billion
596 mm²
Die Size
470 mm²
Graphics Features
12 (12_0)
DirectX
11.1 (10_0)
4.6
OpenGL
3.3
2.1
OpenCL
1.1
1.2.170
Vulkan
N/A
-
CUDA
1.3
6.5
Shader Model
4.0
