AMD Radeon Instinct MI6 vs NVIDIA A10G
We compared two Professional market GPUs: 8GB VRAM Radeon Instinct MI6 and 12GB VRAM A10G to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA A10G 's Advantages
Released 4 years and 4 months late
Boost Clock has increased by 39% (1710MHz vs 1233MHz)
More VRAM (12GB vs 8GB)
Larger VRAM bandwidth (600.2GB/s vs 224.0GB/s)
6912 additional rendering cores
Score
Benchmark
FP32 (float)
Radeon Instinct MI6
5.682 TFLOPS
A10G
+454%
31.52 TFLOPS
Graphics Card
Dec 2016
Release Date
Apr 2021
Radeon Instinct
Generation
Tesla
Professional
Type
Professional
PCIe 3.0 x16
Bus Interface
PCIe 4.0 x16
Clock Speeds
1120 MHz
Base Clock
1320 MHz
1233 MHz
Boost Clock
1710 MHz
1750 MHz
Memory Clock
1563 MHz
Memory
8GB
Memory Size
12GB
GDDR5
Memory Type
GDDR6
256bit
Memory Bus
384bit
224.0GB/s
Bandwidth
600.2GB/s
Render Config
36
Compute Units
-
-
SM Count
72
2304
Shading Units
9216
144
TMUs
288
32
ROPs
96
-
Tensor Cores
288
-
RT Cores
72
16 KB (per CU)
L1 Cache
128 KB (per SM)
2 MB
L2 Cache
6 MB
-
-
-
Theoretical Performance
39.46 GPixel/s
Pixel Rate
164.2 GPixel/s
177.6 GTexel/s
Texture Rate
492.5 GTexel/s
5.682 TFLOPS
FP16 (half)
31.52 TFLOPS
5.682 TFLOPS
FP32 (float)
31.52 TFLOPS
355.1 GFLOPS
FP64 (double)
985.0 GFLOPS
Board Design
150W
TDP
150W
450 W
Suggested PSU
450 W
No outputs
Outputs
No outputs
1x 6-pin
Power Connectors
8-pin EPS
Graphics Processor
Ellesmere
GPU Name
GA102
Ellesmere XT
GPU Variant
GA102-890-A1
GCN 4.0
Architecture
Ampere
GlobalFoundries
Foundry
Samsung
14 nm
Process Size
8 nm
5.7 billion
Transistors
28.3 billion
232 mm²
Die Size
628 mm²
Graphics Features
12 (12_0)
DirectX
12 Ultimate (12_2)
4.6
OpenGL
4.6
2.1
OpenCL
3.0
1.2
Vulkan
1.3
-
CUDA
8.6
6.4
Shader Model
6.6
