NVIDIA GeForce RTX 3090 对 NVIDIA RTX A5500. 规格、性能、测试

显卡的基本技术数据比较 NVIDIA GeForce RTX 3090 和 NVIDIA RTX A5500, 芯片，信息处理单元.

• 建筑学
  Ampere Ampere
• CUDA Cores
  10496 -
• Execution Units
  82 80
• GPU芯片
  GA102-300-A1 GA102
• 渲染输出单位
  112 96
• 着色器
  10496 10240
• 纹理单位
  328 320
• L1 Cache
  - 128 KB
• L2 Cache
  - 6 MB

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

• Memory Bandwidth
  936 GB/s 768 GB/s
• Memory Bus
  384 bit 384 bit
• Memory Clock
  1219 MHz 2000 MHz
• Memory Data Rate
  19.5 Gbps 16 Gbps
• 内存大小
  24 GB 24 GB
• 存储器类型
  GDDR6X GDDR6

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

• 基准频率
  1400 MHz 1170 MHz
• 最大频率
  1700 MHz 1695 MHz

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

• Graphics Card Power
  350 W -
• Maximum GPU Temperature
  93 °C -
• System Power Supply
  750 W (System power requirement) -
• TDP
  350 W 230 W

连通性和连接.

• DisplayPort Ports
  3 × DisplayPort 4 × DisplayPort 1.4a
• HDCP Version
  2.3 -
• 最大。显示
  4 -
• Other Display Outputs (unparsed)
  HDMI -
• PCIe Interface
  PCIe 4.0 x16 PCIe 4.0 x16
• Power Connectors
  2x PCIe 8-pin (adapter to 1x 12-pin included) 1x 8-pin

在电脑游戏中被充分使用的技术数据.

• DirectX
  12_2 12_2
• 最大分辨率
  7680 × 4320 7680 x 4320 at 60 Hz
• OpenCL
  3.0 3.0
• OpenGL
  4.6 4.6
• Shader Model
  6.6 6.6
• Vulkan
  1.3 1.3

内置对视频和图像压缩标准的支持.

• AV1
  Decode -
• h264
  Decode / Encode -
• h265 / HEVC
  Decode / Encode -
• VP8
  Decode -
• VP9
  Decode -

所比较的设备在尺寸、重量和插槽上的差异

• 长度
  - 267 mm
• Slot Size
  - Dual-slot
• Width
  - 112 mm

GPU的接口和发布日期的比较 NVIDIA RTX A5500 和 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. -
• Official source
  https://www.nvidia.com/en-us/geforce/graphics-cards/compare/ -
• Process Technology
  8 nm 8 nm
• 发布日期
  Q3/2020 -
• Verification scope
  Explicit manufacturer fields refreshed; other original historical fields retained, not all reverified. Partial composite conflicts are preserved. -
• Verified on
  2026-09-30 -

• FP16 (theoretical)
  35.58 TFLOPS 34.71 TFLOPS
• FP32 (theoretical)
  - 34.71 TFLOPS
• FP64 (theoretical)
  - 1,085 GFLOPS
• Pixel Rate
  189.8 GPixel/s 162.7 GPixel/s
• Texture Rate
  556.0 GTexel/s 542.4 GTexel/s