A10G vs Radeon Instinct MI8
We compared two Professional market GPUs: 12GB VRAM A10G and 4GB VRAM Radeon Instinct MI8 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
A10G 's Advantages
Released 4 years and 4 months late
Boost Clock1710MHz
More VRAM (12GB vs 4GB)
Larger VRAM bandwidth (600.2GB/s vs 512.0GB/s)
5120 additional rendering cores
Lower TDP (150W vs 175W)
Score
Benchmark
FP32 (float)
A10G
+284%
31520
Radeon Instinct MI8
8192
Graphics Card
Apr 2021
Release Date
Dec 2016
Tesla
Generation
Radeon Instinct
Professional
Type
Professional
PCIe 4.0 x16
Bus Interface
PCIe 3.0 x16
Clock Speeds
1320 MHz
Base Clock
-
1710 MHz
Boost Clock
-
1563 MHz
Memory Clock
500 MHz
Memory
12GB
Memory Size
4GB
GDDR6
Memory Type
HBM
384bit
Memory Bus
4096bit
600.2GB/s
Bandwidth
512.0GB/s
Render Config
-
Compute Units
64
72
SM Count
-
9216
Shading Units
4096
288
TMUs
256
96
ROPs
64
288
Tensor Cores
-
72
RT Cores
-
128 KB (per SM)
L1 Cache
16 KB (per CU)
6 MB
L2 Cache
2 MB
Theoretical Performance
164.2 GPixel/s
Pixel Rate
64.00 GPixel/s
492.5 GTexel/s
Texture Rate
256.0 GTexel/s
31.52 TFLOPS
FP16 (half)
8.192 TFLOPS
31.52 TFLOPS
FP32 (float)
8.192 TFLOPS
985.0 GFLOPS
FP64 (double)
512.0 GFLOPS
Board Design
150W
TDP
175W
450 W
Suggested PSU
450 W
No outputs
Outputs
No outputs
8-pin EPS
Power Connectors
1x 8-pin
Graphics Processor
GA102
GPU Name
Fiji
GA102-890-A1
GPU Variant
Fiji XT CA
(215-0862120)
Ampere
Architecture
GCN 3.0
Samsung
Foundry
TSMC
8 nm
Process Size
28 nm
28.3 billion
Transistors
8.9 billion
628 mm²
Die Size
596 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
12 (12_0)
4.6
OpenGL
4.6
3.0
OpenCL
2.1
1.3
Vulkan
1.2.170
8.6
CUDA
-
6.6
Shader Model
6.5
