AMD Radeon Instinct MI100 vs NVIDIA GRID M40
We compared two Professional market GPUs: 32GB VRAM Radeon Instinct MI100 and 8GB VRAM GRID M40 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
AMD Radeon Instinct MI100 's Advantages
Released 4 years and 6 months late
Boost Clock1502MHz
More VRAM (32GB vs 8GB)
Larger VRAM bandwidth (1229GB/s vs 83.20GB/s)
7296 additional rendering cores
NVIDIA GRID M40 's Advantages
Lower TDP (50W vs 300W)
Score
Benchmark
FP32 (float)
Radeon Instinct MI100
+2809%
23.07 TFLOPS
GRID M40
0.793 TFLOPS
Graphics Card
Nov 2020
Release Date
May 2016
Radeon Instinct
Generation
GRID
Professional
Type
Professional
PCIe 4.0 x16
Bus Interface
PCIe 3.0 x16
Clock Speeds
1000 MHz
Base Clock
-
1502 MHz
Boost Clock
-
1200 MHz
Memory Clock
1300 MHz
Memory
32GB
Memory Size
8GB
HBM2
Memory Type
GDDR5
4096bit
Memory Bus
128bit
1229GB/s
Bandwidth
83.20GB/s
Render Config
120
Compute Units
-
-
-
-
7680
Shading Units
384
480
TMUs
32
64
ROPs
16
-
-
-
-
-
-
16 KB (per CU)
L1 Cache
64 KB (per SMM)
8 MB
L2 Cache
2 MB
-
-
-
Theoretical Performance
96.13 GPixel/s
Pixel Rate
16.53 GPixel/s
721.0 GTexel/s
Texture Rate
33.06 GTexel/s
184.6 TFLOPS
FP16 (half)
-
23.07 TFLOPS
FP32 (float)
793.3 GFLOPS
11.54 TFLOPS
FP64 (double)
24.79 GFLOPS
Board Design
300W
TDP
50W
700 W
Suggested PSU
250 W
No outputs
Outputs
No outputs
2x 8-pin
Power Connectors
-
Graphics Processor
Arcturus
GPU Name
GM107
Arcturus XL
GPU Variant
-
CDNA 1.0
Architecture
Maxwell
TSMC
Foundry
TSMC
7 nm
Process Size
28 nm
25.6 billion
Transistors
1.87 billion
750 mm²
Die Size
148 mm²
Graphics Features
N/A
DirectX
12 (11_0)
N/A
OpenGL
4.6
2.1
OpenCL
3.0
N/A
Vulkan
1.3
-
CUDA
5.0
N/A
Shader Model
5.1
