AMD Radeon Instinct MI100 vs NVIDIA RTX A2000
We compared two Professional market GPUs: 32GB VRAM Radeon Instinct MI100 and 6GB VRAM RTX A2000 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
AMD Radeon Instinct MI100 's Advantages
Boost Clock has increased by 25% (1502MHz vs 1200MHz)
More VRAM (32GB vs 6GB)
Larger VRAM bandwidth (1229GB/s vs 288.0GB/s)
4352 additional rendering cores
NVIDIA RTX A2000 's Advantages
Released 9 months late
Lower TDP (70W vs 300W)
Score
Benchmark
FP32 (float)
Radeon Instinct MI100
+188%
23.07 TFLOPS
RTX A2000
7.987 TFLOPS
Graphics Card
Nov 2020
Release Date
Aug 2021
Radeon Instinct
Generation
Quadro Ampere
Professional
Type
Professional
PCIe 4.0 x16
Bus Interface
PCIe 4.0 x16
Clock Speeds
1000 MHz
Base Clock
562 MHz
1502 MHz
Boost Clock
1200 MHz
1200 MHz
Memory Clock
1500 MHz
Memory
32GB
Memory Size
6GB
HBM2
Memory Type
GDDR6
4096bit
Memory Bus
192bit
1229GB/s
Bandwidth
288.0GB/s
Render Config
120
Compute Units
-
-
SM Count
26
7680
Shading Units
3328
480
TMUs
104
64
ROPs
48
-
Tensor Cores
104
-
RT Cores
26
16 KB (per CU)
L1 Cache
128 KB (per SM)
8 MB
L2 Cache
3 MB
-
-
-
Theoretical Performance
96.13 GPixel/s
Pixel Rate
57.60 GPixel/s
721.0 GTexel/s
Texture Rate
124.8 GTexel/s
184.6 TFLOPS
FP16 (half)
7.987 TFLOPS
23.07 TFLOPS
FP32 (float)
7.987 TFLOPS
11.54 TFLOPS
FP64 (double)
124.8 GFLOPS
Board Design
300W
TDP
70W
700 W
Suggested PSU
250 W
No outputs
Outputs
4x mini-DisplayPort 1.4a
2x 8-pin
Power Connectors
None
Graphics Processor
Arcturus
GPU Name
GA106
Arcturus XL
GPU Variant
GA106-850-A1
CDNA 1.0
Architecture
Ampere
TSMC
Foundry
Samsung
7 nm
Process Size
8 nm
25.6 billion
Transistors
12 billion
750 mm²
Die Size
276 mm²
Graphics Features
N/A
DirectX
12 Ultimate (12_2)
N/A
OpenGL
4.6
2.1
OpenCL
3.0
N/A
Vulkan
1.3
-
CUDA
8.6
N/A
Shader Model
6.7
