NVIDIA GeForce RTX 4070 SUPER 对 NVIDIA A800 SXM4 80 GB. 规格

显卡的基本技术数据比较 NVIDIA GeForce RTX 4070 SUPER 和 NVIDIA A800 SXM4 80 GB, 芯片，信息处理单元.

• 建筑学
  Ada Lovelace Ampere
• 基于
  NVIDIA GeForce RTX 4070 SUPER -
• CUDA Cores
  7168 -
• 着色器
  7168 -
• Execution Units
  - 6912
• GPU芯片
  - GA100
• L1 Cache
  - 192 KB
• L2 Cache
  - 40 MB
• 渲染输出单位
  - 160
• 纹理单位
  - 432

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

• Memory Bus
  192 bit 5120 bit
• 内存大小
  12 GB 80 GB
• 存储器类型
  GDDR6X HBM2e
• Memory Bandwidth
  - 0.255 GB/s
• Memory Clock
  - 1593 MHz

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

• 基准频率
  1980 MHz 1275 MHz
• 最大频率
  2480 MHz 1410 MHz

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

• Maximum GPU Temperature
  90 °C -
• System Power Supply
  650 W (System power requirement) -
• TDP
  220 W 400 W

连通性和连接.

• PCIe Interface
  4.0 PCIe 4.0 x16
• 最大。显示
  - 1
• Power Connectors
  - 没有

在电脑游戏中被充分使用的技术数据.

• CUDA
  - 8.0
• DirectX
  - 12.2
• 最大分辨率
  - 3840 × 2160
• OpenCL
  - 3.0

内置对视频和图像压缩标准的支持.

• AV1
  Decode / Encode -

所比较的设备在尺寸、重量和插槽上的差异

• Slot Size
  - IGP

GPU的接口和发布日期的比较 NVIDIA A800 SXM4 80 GB 和 NVIDIA GeForce RTX 4070 SUPER.

• Official source
  https://www.nvidia.com/en-us/geforce/graphics-cards/40-series/rtx-4070-family/ -
• Specification source
  https://www.nvidia.com/en-us/geforce/graphics-cards/compare/ -
• Verified on
  2026-09-30 -
• Process Technology
  - 7 nm
• 发布日期
  - Q3/2022

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