NVIDIA A100 SXM4 40 GB vs AMD Radeon RX Vega XT

Comparative analysis of NVIDIA A100 SXM4 40 GB and AMD Radeon RX Vega XT videocards for all known characteristics in the following categories: Essentials, Technical info, Video outputs and ports, Compatibility, dimensions and requirements, API support, Memory. Benchmark videocards performance analysis: Geekbench - OpenCL.

 

Differences

Reasons to consider the NVIDIA A100 SXM4 40 GB

  • Videocard is newer: launch date 2 year(s) 9 month(s) later
  • 1459.6x more texture fill rate: 609.1 GTexel/s vs 417.3 GTexel / s
  • Around 69% higher pipelines: 6912 vs 4096
  • A newer manufacturing process allows for a more powerful, yet cooler running videocard: 7 nm vs 14 nm
  • 5x more maximum memory size: 40 GB vs 8 GB
Launch date 14 May 2020 vs 8 August 2017
Texture fill rate 609.1 GTexel/s vs 417.3 GTexel / s
Pipelines 6912 vs 4096
Manufacturing process technology 7 nm vs 14 nm
Maximum memory size 40 GB vs 8 GB

Reasons to consider the AMD Radeon RX Vega XT

  • Around 37% higher core clock speed: 1500 MHz vs 1095 MHz
  • Around 16% higher boost clock speed: 1630 MHz vs 1410 MHz
  • Around 78% lower typical power consumption: 225 Watt vs 400 Watt
  • Around 56% higher memory clock speed: 1890 MHz vs 1215 MHz (2.4 Gbps effective)
  • Around 3% better performance in Geekbench - OpenCL: 196748 vs 191749
Specifications (specs)
Core clock speed 1500 MHz vs 1095 MHz
Boost clock speed 1630 MHz vs 1410 MHz
Thermal Design Power (TDP) 225 Watt vs 400 Watt
Memory clock speed 1890 MHz vs 1215 MHz (2.4 Gbps effective)
Benchmarks
Geekbench - OpenCL 196748 vs 191749

Compare benchmarks

GPU 1: NVIDIA A100 SXM4 40 GB
GPU 2: AMD Radeon RX Vega XT

Geekbench - OpenCL
GPU 1
GPU 2
191749
196748
Name NVIDIA A100 SXM4 40 GB AMD Radeon RX Vega XT
Geekbench - OpenCL 191749 196748

Compare specifications (specs)

NVIDIA A100 SXM4 40 GB AMD Radeon RX Vega XT

Essentials

Architecture Ampere GCN 5.0
Code name GA100 Vega 10
Launch date 14 May 2020 8 August 2017
Place in performance rating 3 2
Type Desktop

Technical info

Boost clock speed 1410 MHz 1630 MHz
Core clock speed 1095 MHz 1500 MHz
Manufacturing process technology 7 nm 14 nm
Peak Double Precision (FP64) Performance 9.746 TFLOPS (1:2)
Peak Half Precision (FP16) Performance 77.97 TFLOPS (4:1)
Peak Single Precision (FP32) Performance 19.49 TFLOPS
Pipelines 6912 4096
Pixel fill rate 225.6 GPixel/s
Texture fill rate 609.1 GTexel/s 417.3 GTexel / s
Thermal Design Power (TDP) 400 Watt 225 Watt
Transistor count 54200 million
Floating-point performance 13,353 gflops

Video outputs and ports

Display Connectors No outputs 1x HDMI, 3x DisplayPort

Compatibility, dimensions and requirements

Form factor IGP
Interface PCIe 4.0 x16 PCIe 3.0 x16
Recommended system power (PSU) 800 Watt
Supplementary power connectors None 2x 8-pin
Length 267 mm

API support

OpenCL 3.0

Memory

High bandwidth memory (HBM)
Maximum RAM amount 40 GB 8 GB
Memory bandwidth 1555 GB/s 483.8 GB / s
Memory bus width 5120 bit 2048 Bit
Memory clock speed 1215 MHz (2.4 Gbps effective) 1890 MHz
Memory type HBM2e HBM2