NVIDIA GRID K2 vs NVIDIA Tesla D870
We compared two Professional market GPUs: 4GB VRAM GRID K2 and 1536MB VRAM Tesla D870 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA GRID K2 's Advantages
Released 6 years late
More VRAM (4GB vs 1536GB)
Larger VRAM bandwidth (160.0GB/s vs 76.80GB/s)
1408 additional rendering cores
Lower TDP (225W vs 520W)
Score
Benchmark
FP32 (float)
GRID K2
+561%
2.289 TFLOPS
Tesla D870
0.346 TFLOPS
Graphics Card
May 2013
Release Date
May 2007
GRID
Generation
Tesla
Professional
Type
Professional
PCIe 3.0 x16
Bus Interface
PCIe 1.0 x16
Clock Speeds
-
-
-
-
-
-
1250 MHz
Memory Clock
800 MHz
Memory
4GB
Memory Size
1536MB
GDDR5
Memory Type
GDDR3
256bit
Memory Bus
384bit
160.0GB/s
Bandwidth
76.80GB/s
Render Config
-
-
-
-
SM Count
16
1536
Shading Units
128
128
TMUs
32
32
ROPs
24
-
-
-
-
-
-
16 KB (per SMX)
L1 Cache
-
512 KB
L2 Cache
96 KB
-
-
-
Theoretical Performance
23.84 GPixel/s
Pixel Rate
14.40 GPixel/s
95.36 GTexel/s
Texture Rate
38.40 GTexel/s
-
-
-
2.289 TFLOPS
FP32 (float)
345.6 GFLOPS
95.36 GFLOPS
FP64 (double)
-
Board Design
225W
TDP
520W
550 W
Suggested PSU
900 W
No outputs
Outputs
No outputs
1x 6-pin + 1x 8-pin
Power Connectors
-
Graphics Processor
GK104
GPU Name
G80
GK104-895-A2
GPU Variant
-
Kepler
Architecture
Tesla
TSMC
Foundry
TSMC
28 nm
Process Size
90 nm
3.54 billion
Transistors
0.681 billion
294 mm²
Die Size
484 mm²
Graphics Features
12 (11_0)
DirectX
11.1 (10_0)
4.6
OpenGL
3.3
3.0
OpenCL
1.1 (1.0)
1.2.175
Vulkan
N/A
3.0
CUDA
1.0
6.5 (5.1)
Shader Model
4.0
