NVIDIA A100 PCIe 80 GB vs NVIDIA Tesla S1075

Comparison of NVIDIA A100 PCIe 80 GB with 80 GB HBM2e and 6,912 cores vs NVIDIA Tesla S1075 with 4 GB GDDR3 and 240 cores.

Loading...

Performance Rating

A100 A100
H200 H200
MI325X MI325X

NVIDIA A100 PCIe 80 GB

25.6

NVIDIA A100 PCIe 80 GB

25.6
RX 7900 XTX RX 7900 XTX
MI250 MI250
Instinct MI300X Instinct MI300X

NVIDIA Tesla S1075

NVIDIA Tesla S1075

Contents:

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

Memory

Memory Size

🔥 +1,900% 80 ГБ
4 GB ×4 (16 ГБ)

Memory Type

HBM2e GDDR3

Memory Bandwidth

🔥 1.94 TB/s
102.4 GB/s ×4 (409.6 GB/s)

Memory Bus Width

5,120 бит 512 бит ×4 (2048 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)

🔥 +3,033% 19.49 TFLOPS
0.6221 TFLOPS

FP64 (Double Precision)

🔥 +12,427% 9.746 TFLOPS
0.0778 TFLOPS

CUDA Cores

🔥 +2,780% 6,912
240 ×4 (960)

RT Cores

No No

Architecture & Compatibility

GPU Architecture

Ampere Tesla 2.0

SM (Streaming Multiprocessor)

🔥 +260% 108
30

PCIe Version

PCIe 4.0 x16 PCIe 2.0 x16

ML Software Support

CUDA Version

🔥 8.0
1.3

Clocks & Performance

Base Clock

🔥 1,065
No

Boost Clock

🔥 1,410
No

Memory Clock

🔥 +89% 1,512
800

Power Consumption

TDP/TGP

🔥 -62% 300 W
800 W

Recommended PSU

🔥 -42% 700 W
1200 W

Power Connector

8-pin EPS No

Rendering

Texture Units (TMU)

🔥 +440% 432
80 ×4 (320)

ROP

No No

L2 Cache

🔥 80 MB
256 KB

Additional

Slots

Dual-slot Dual-slot

Release Date

June 28, 2021 June 1, 2008

Display Outputs

No outputs
No outputs

Renting is cheaper than buying