Tesla D870 vs GRID M40
We compared two Professional market GPUs: 1536MB VRAM Tesla D870 and 8GB VRAM GRID M40 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
GRID M40 's Advantages
Released 9 years late
More VRAM (8GB vs 1536GB)
Larger VRAM bandwidth (83.20GB/s vs 76.80GB/s)
256 additional rendering cores
Lower TDP (50W vs 520W)
Score
Benchmark
FP32 (float)
Tesla D870
346
GRID M40
+129%
793
Graphics Card
May 2007
Release Date
May 2016
Tesla
Generation
GRID
Professional
Type
Professional
PCIe 1.0 x16
Bus Interface
PCIe 3.0 x16
Clock Speeds
800 MHz
Memory Clock
1300 MHz
Memory
1536MB
Memory Size
8GB
GDDR3
Memory Type
GDDR5
384bit
Memory Bus
128bit
76.80GB/s
Bandwidth
83.20GB/s
Render Config
16
SM Count
-
128
Shading Units
384
32
TMUs
32
24
ROPs
16
-
L1 Cache
64 KB (per SMM)
96 KB
L2 Cache
2 MB
Theoretical Performance
14.40 GPixel/s
Pixel Rate
16.53 GPixel/s
38.40 GTexel/s
Texture Rate
33.06 GTexel/s
345.6 GFLOPS
FP32 (float)
793.3 GFLOPS
-
FP64 (double)
24.79 GFLOPS
Board Design
520W
TDP
50W
900 W
Suggested PSU
250 W
No outputs
Outputs
No outputs
Graphics Processor
G80
GPU Name
GM107
Tesla
Architecture
Maxwell
TSMC
Foundry
TSMC
90 nm
Process Size
28 nm
0.681 billion
Transistors
1.87 billion
484 mm²
Die Size
148 mm²
Graphics Features
11.1 (10_0)
DirectX
12 (11_0)
3.3
OpenGL
4.6
1.1 (1.0)
OpenCL
3.0
N/A
Vulkan
1.3
1.0
CUDA
5.0
4.0
Shader Model
5.1
