NVIDIA A800 SXM4 80 GB vs NVIDIA Tesla K40d

Comparison of NVIDIA A800 SXM4 80 GB with 80 GB HBM2e and 6,912 cores vs NVIDIA Tesla K40d with 12 GB GDDR5 and 2,880 cores.

Loading...

Performance Rating

NVIDIA A800 SXM4 80 GB outperforms NVIDIA Tesla K40d by 436.02% in the overall GPU ARK performance rating

A100 A100
H200 H200
MI325X MI325X

NVIDIA A800 SXM4 80 GB

25.9

NVIDIA A800 SXM4 80 GB

25.9
RX 7900 XTX RX 7900 XTX
MI250 MI250
Instinct MI300X Instinct MI300X

NVIDIA Tesla K40d

4.8

NVIDIA Tesla K40d

4.8

Contents:

Memory ML Performance Compute Power Architecture & Compatibility ML Software Support Clocks & Performance Power Consumption Rendering Additional

Memory

Memory Size

🔥 +567% 80 ГБ
12 ГБ

Memory Type

HBM2e GDDR5

Memory Bandwidth

🔥 2.04 TB/s
288.4 GB/s

Memory Bus Width

5,120 бит 384 бит

ML Performance

FP16 (Half Precision)

🔥 77.97 TFLOPS
No

BF16 (Brain Float)

🔥 311.84 TFLOPS
No

TF32 (TensorFloat)

🔥 155.92
No

Compute Power

FP32 (Single Precision)

🔥 +286% 19.49 TFLOPS
5.046 TFLOPS

FP64 (Double Precision)

🔥 +479% 9.746 TFLOPS
1.682 TFLOPS

CUDA Cores

🔥 +140% 6,912
2,880

RT Cores

No No

Architecture & Compatibility

GPU Architecture

Ampere Kepler

SM (Streaming Multiprocessor)

🔥 108
No

PCIe Version

PCIe 4.0 x16 PCIe 3.0 x16

ML Software Support

CUDA Version

🔥 8.0
3.5

Clocks & Performance

Base Clock

🔥 +55% 1,155
745

Boost Clock

🔥 +61% 1,410
876

Memory Clock

🔥 +6% 1,593
1,502

Power Consumption

TDP/TGP

400 W
🔥 -39% 245 W

Recommended PSU

800 W
🔥 -31% 550 W

Power Connector

None No

Rendering

Texture Units (TMU)

🔥 +80% 432
240

ROP

No No

L2 Cache

🔥 40 MB
1536 KB

Additional

Slots

🔥 SXM Module
Dual-slot

Release Date

Aug. 11, 2022 Nov. 22, 2013

Display Outputs

No outputs
No outputs

Renting is cheaper than buying