NVIDIA A100 PCIe 80 GB vs PowerColor HD 6990

Comparison of NVIDIA A100 PCIe 80 GB with 80 GB HBM2e and 6,912 cores vs PowerColor HD 6990 with 2 GB GDDR5 and 1,536 cores.

Loading...

Performance Rating

NVIDIA A100 PCIe 80 GB outperforms PowerColor HD 6990 by 1,081.11% in the overall GPU ARK 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

PowerColor HD 6990

2.2

PowerColor HD 6990

2.2

Contents:

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

Memory

Memory Size

🔥 +3,900% 80 ГБ
2 ГБ ×2 (4 ГБ)

Memory Type

HBM2e GDDR5

Memory Bandwidth

🔥 1.94 TB/s
160.0 GB/s ×2 (320 GB/s)

Memory Bus Width

5,120 бит 256 бит ×2 (512 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)

🔥 +664% 19.49 TFLOPS
2.55 TFLOPS

FP64 (Double Precision)

🔥 +1,429% 9.746 TFLOPS
0.6374 TFLOPS

CUDA Cores

🔥 +350% 6,912
1,536 ×2 (3072)

RT Cores

No No

Architecture & Compatibility

GPU Architecture

Ampere TeraScale 3

SM (Streaming Multiprocessor)

🔥 108
No

PCIe Version

PCIe 4.0 x16 PCIe 2.0 x16

ML Software Support

CUDA Version

8.0 No

Clocks & Performance

Base Clock

🔥 1,065
No

Boost Clock

🔥 1,410
No

Memory Clock

🔥 +21% 1,512
1,250

Power Consumption

TDP/TGP

🔥 -20% 300 W
375 W

Recommended PSU

🔥 -7% 700 W
750 W

Power Connector

8-pin EPS 2x 8-pin

Rendering

Texture Units (TMU)

🔥 +350% 432
96 ×2 (192)

ROP

No No

L2 Cache

🔥 80 MB
512 KB

Additional

Slots

Dual-slot Dual-slot

Release Date

June 28, 2021 March 8, 2011

Display Outputs

No outputs
1x DVI
4x mini-DisplayPort 1.2

Renting is cheaper than buying