Tesla P4 vs Tesla K40m
We compared two Professional market GPUs: 8GB VRAM Tesla P4 and 12GB VRAM Tesla K40m to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
Tesla P4 's Advantages
Released 2 years and 10 months late
Boost Clock has increased by 27% (1114MHz vs 876MHz)
Lower TDP (75W vs 245W)
Tesla K40m 's Advantages
More VRAM (12GB vs 8GB)
Larger VRAM bandwidth (288.4GB/s vs 192.3GB/s)
320 additional rendering cores
Score
Benchmark
FP32 (float)
Tesla P4
+13%
5704
Tesla K40m
5046
OctaneBench
Tesla P4
+25%
85
Tesla K40m
68
Graphics Card
Sep 2016
Release Date
Nov 2013
Tesla
Generation
Tesla
Professional
Type
Professional
PCIe 3.0 x16
Bus Interface
PCIe 3.0 x16
Clock Speeds
886 MHz
Base Clock
745 MHz
1114 MHz
Boost Clock
876 MHz
1502 MHz
Memory Clock
1502 MHz
Memory
8GB
Memory Size
12GB
GDDR5
Memory Type
GDDR5
256bit
Memory Bus
384bit
192.3GB/s
Bandwidth
288.4GB/s
Render Config
20
SM Count
-
2560
Shading Units
2880
160
TMUs
240
64
ROPs
48
48 KB (per SM)
L1 Cache
16 KB (per SMX)
2 MB
L2 Cache
1536 KB
Theoretical Performance
71.30 GPixel/s
Pixel Rate
52.56 GPixel/s
178.2 GTexel/s
Texture Rate
210.2 GTexel/s
89.12 GFLOPS
FP16 (half)
-
5.704 TFLOPS
FP32 (float)
5.046 TFLOPS
178.2 GFLOPS
FP64 (double)
1.682 TFLOPS
Board Design
75W
TDP
245W
250 W
Suggested PSU
550 W
No outputs
Outputs
No outputs
None
Power Connectors
-
Graphics Processor
GP104
GPU Name
GK110B
GP104-895-A1
GPU Variant
-
Pascal
Architecture
Kepler
TSMC
Foundry
TSMC
16 nm
Process Size
28 nm
7.2 billion
Transistors
7.08 billion
314 mm²
Die Size
561 mm²
Graphics Features
12 (12_1)
DirectX
12 (11_1)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.3
Vulkan
1.1
6.1
CUDA
3.5
6.4
Shader Model
5.1
