Diamond HD 6990 vs NVIDIA A100 PCIe 80 GB

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

Loading...

Performance Rating

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

A100 A100
H200 H200
MI325X MI325X

Diamond HD 6990

2.2

Diamond HD 6990

2.2
RX 7900 XTX RX 7900 XTX
MI250 MI250
Instinct MI300X Instinct MI300X

NVIDIA A100 PCIe 80 GB

25.6

NVIDIA A100 PCIe 80 GB

25.6

Contents:

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

Memory

Memory Size

2 ГБ ×2 (4 ГБ)
🔥 +3,900% 80 ГБ

Memory Type

GDDR5 HBM2e

Memory Bandwidth

160.0 GB/s ×2 (320 GB/s)
🔥 1.94 TB/s

Memory Bus Width

256 бит ×2 (512 бит) 5,120 бит

ML Performance

FP16 (Half Precision)

No
🔥 77.97 TFLOPS

BF16 (Brain Float)

No
🔥 311.84 TFLOPS

TF32 (TensorFloat)

No
🔥 155.92

Compute Power

FP32 (Single Precision)

2.55 TFLOPS
🔥 +664% 19.49 TFLOPS

FP64 (Double Precision)

0.6374 TFLOPS
🔥 +1,429% 9.746 TFLOPS

CUDA Cores

1,536 ×2 (3072)
🔥 +350% 6,912

RT Cores

No No

Architecture & Compatibility

GPU Architecture

TeraScale 3 Ampere

SM (Streaming Multiprocessor)

No
🔥 108

PCIe Version

PCIe 2.0 x16 PCIe 4.0 x16

ML Software Support

CUDA Version

No 8.0

Clocks & Performance

Base Clock

No
🔥 1,065

Boost Clock

No
🔥 1,410

Memory Clock

1,250
🔥 +21% 1,512

Power Consumption

TDP/TGP

375 W
🔥 -20% 300 W

Recommended PSU

750 W
🔥 -7% 700 W

Power Connector

2x 8-pin 8-pin EPS

Rendering

Texture Units (TMU)

96 ×2 (192)
🔥 +350% 432

ROP

No No

L2 Cache

512 KB
🔥 80 MB

Additional

Slots

Dual-slot Dual-slot

Release Date

March 8, 2011 June 28, 2021

Display Outputs

1x DVI
4x mini-DisplayPort 1.2
No outputs

Renting is cheaper than buying