Home GPU Comparison NVIDIA Tesla K40s vs NVIDIA A10 PCIe

NVIDIA Tesla K40s vs NVIDIA A10 PCIe

We compared two Professional market GPUs: 12GB VRAM Tesla K40s and 24GB VRAM A10 PCIe to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.

Main Differences

NVIDIA A10 PCIe 's Advantages
Released 7 years and 5 months late
Boost Clock has increased by 93% (1695MHz vs 876MHz)
More VRAM (24GB vs 12GB)
Larger VRAM bandwidth (600.2GB/s vs 288.4GB/s)
6336 additional rendering cores
Lower TDP (150W vs 245W)

Score

Benchmark

FP32 (float)
Tesla K40s
5.046 TFLOPS
A10 PCIe +519%
31.24 TFLOPS
VS

Graphics Card

Nov 2013
Release Date
Apr 2021
Tesla
Generation
Tesla
Professional
Type
Professional
PCIe 3.0 x16
Bus Interface
PCIe 4.0 x16

Clock Speeds

745 MHz
Base Clock
885 MHz
876 MHz
Boost Clock
1695 MHz
1502 MHz
Memory Clock
1563 MHz

Memory

12GB
Memory Size
24GB
GDDR5
Memory Type
GDDR6
384bit
Memory Bus
384bit
288.4GB/s
Bandwidth
600.2GB/s

Render Config

-
SM Count
72
-
Compute Units
-
2880
Shading Units
9216
240
TMUs
288
48
ROPs
96
-
Tensor Cores
288
-
RT Cores
72
16 KB (per SMX)
L1 Cache
128 KB (per SM)
1536 KB
L2 Cache
6 MB

Theoretical Performance

52.56 GPixel/s
Pixel Rate
162.7 GPixel/s
210.2 GTexel/s
Texture Rate
488.2 GTexel/s
-
FP16 (half)
31.24 TFLOPS
5.046 TFLOPS
FP32 (float)
31.24 TFLOPS
1.682 TFLOPS
FP64 (double)
976.3 GFLOPS

Graphics Processor

GK110B
GPU Name
GA102
-
GPU Variant
GA102-890-A1
Kepler
Architecture
Ampere
TSMC
Foundry
Samsung
28 nm
Process Size
8 nm
7.08 billion
Transistors
28.3 billion
561 mm²
Die Size
628 mm²

Board Design

245W
TDP
150W
550 W
Suggested PSU
450 W
No outputs
Outputs
No outputs
-
Power Connectors
1x 8-pin

Graphics Features

12 (11_1)
DirectX
12 Ultimate (12_2)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.1
Vulkan
1.3
3.5
CUDA
8.6
5.1
Shader Model
6.6

Related GPU Comparisons

© 2024 - TopCPU.net   Contact Us Privacy Policy