Select processor 1
Select processor 2
NVIDIA GeForce RTX 3090
NVIDIA A800 PCIe 40 GB

NVIDIA GeForce RTX 3090 vs NVIDIA A800 PCIe 40 GB. Specifications, performance, tests

User rating
star star star star star
Released
Q3/2020
NVIDIA GeForce RTX 3090
NVIDIA GeForce RTX 3090
Released
Q3/2022
User rating
star star star star star
NVIDIA A800 PCIe 40 GB
NVIDIA A800 PCIe 40 GB

What's the best choice NVIDIA GeForce RTX 3090 or NVIDIA A800 PCIe 40 GB? Which graphics card is faster?

Compare the available specifications of these models.

NVIDIA GeForce RTX 3090 has a base frequency of 1.4 GHz. Memory size 24 GB. Memory type GDDR6X. Released in Q3/2020.

NVIDIA A800 PCIe 40 GB has a base frequency of 1.215 GHz. Memory size 40 GB. Memory type HBM2e. Released in Q3/2022.

Differences

  • Higher clock speed

    Around 15% better clock speed

    1.4 GHz left arrow 1.215 GHz

Positions in all rankings

Common positions NVIDIA GeForce RTX 3090 GPU in popular benchmarks, for comparison with other models.

  • Passmark Performance Test GPU
    2 place
  • More memory

    67% more memory

    40 GB left arrow 24 GB

Specifications

Technical data
NVIDIA GeForce RTX 3090 NVIDIA GeForce RTX 3090
NVIDIA A800 PCIe 40 GB NVIDIA A800 PCIe 40 GB
General info

Comparison of basic technical data of graphics cards NVIDIA GeForce RTX 3090 and NVIDIA A800 PCIe 40 GB, chip, information processing units.

  • Architecture
    Ampere left arrow Ampere
  • CUDA Cores
    10496 left arrow -
  • Execution Units
    82 left arrow 6912
  • GPU Chip
    GA102-300-A1 left arrow GA100
  • Render Output Units
    112 left arrow 160
  • Shader
    10496 left arrow -
  • Texture Units
    328 left arrow 432
  • L1 Cache
    - left arrow 192 KB
  • L2 Cache
    - left arrow 40 MB
Memory settings

Video memory capacity, type, bus width and bandwidth describe different properties. These values alone do not determine graphics performance.

  • Memory Bandwidth
    936 GB/s left arrow 1,555 GB/s
  • Memory Bus
    384 bit left arrow 5120 bit
  • Memory Clock
    1219 MHz left arrow 1215 MHz
  • Memory Data Rate
    19.5 Gbps left arrow 2.4 Gbps
  • Memory Size
    24 GB left arrow 40 GB
  • Memory Type
    GDDR6X left arrow HBM2e
Clock frequency

Published GPU clock frequencies describe different operating modes. Clock speed alone does not determine graphics performance.

  • Base Clock
    1400 MHz left arrow 765 MHz
  • Boost Clock
    1700 MHz left arrow 1410 MHz
Thermal Management

Graphics card power limits and recommended system power supply describe different specifications.

  • Graphics Card Power
    350 W left arrow -
  • Maximum GPU Temperature
    93 °C left arrow -
  • System Power Supply
    750 W (System power requirement) left arrow 600 W (PSU recommendation)
  • TDP
    350 W left arrow 250 W
Interfaces

Connectivity and connections.

  • DisplayPort Ports
    3 × DisplayPort left arrow -
  • HDCP Version
    2.3 left arrow -
  • Max. Displays
    4 left arrow -
  • Other Display Outputs (unparsed)
    HDMI left arrow -
  • PCIe Interface
    PCIe 4.0 x16 left arrow PCIe 4.0 x16
  • Power Connectors
    2x PCIe 8-pin (adapter to 1x 12-pin included) left arrow 8-pin EPS
Technical data

Technical data that is used to its full potential in computer games.

  • DirectX
    12_2 left arrow 12.2
  • Max. resolution
    7680 × 4320 left arrow 3840 × 2160
  • OpenCL
    3.0 left arrow 3.0
  • OpenGL
    4.6 left arrow 4.6
  • Shader Model
    6.6 left arrow -
  • Vulkan
    1.3 left arrow -
  • CUDA
    - left arrow 8.0
Supported Video Codecs

Built-in support for video and image compression standards.

  • AV1
    Decode left arrow -
  • h264
    Decode / Encode left arrow -
  • h265 / HEVC
    Decode / Encode left arrow -
  • VP8
    Decode left arrow -
  • VP9
    Decode left arrow -
Dimensions

The difference in size, weight and slot of the compared devices

  • Length
    - left arrow 267 mm
  • Slot Size
    - left arrow Dual-slot
  • Width
    - left arrow 112 mm
More information

Comparison of interfaces and release dates for GPU NVIDIA A800 PCIe 40 GB and NVIDIA GeForce RTX 3090.

  • Manufacturer specification scope
    NVIDIA Founders Edition/reference design. Clock specifications apply to gaming use. AIB shipping specifications and complete-system power needs may differ. left arrow -
  • Process Technology
    8 nm left arrow 7 nm
  • Release date
    Q3/2020 left arrow Q3/2022
Theoretical Performance

  • FP16 (theoretical)
    35.58 TFLOPS left arrow 77.97 TFLOPS (4:1)
  • FP32 (theoretical)
    - left arrow 19.49 TFLOPS
  • FP64 (theoretical)
    - left arrow 9.746 TFLOPS (1:2)
  • Pixel Rate
    189.8 GPixel/s left arrow 225.6 GPixel/s
  • Texture Rate
    556.0 GTexel/s left arrow 609.1 GTexel/s

Benchmarks

Performance tests GPUs
Individual model tests

These results have no shared test of both models with the same version and settings. They are shown separately without a percentage difference.

NVIDIA GeForce RTX 3090

More results: 10

NVIDIA A800 PCIe 40 GB

Individual system tests

Results were obtained on the reported systems. Test versions and settings remain separate; incomplete conditions do not support calculated model performance differences.

Cinebench 2024 / GPU

Model ResultReported conditions
NVIDIA GeForce RTX 3090 19512 points System: GeForce RTX 3090
Graphics: GeForce RTX 3090
Source minimum runtime: 0 minutes.
Exact test build and complete conditions are unreported; no ranking position.

Latest comparisons