NVIDIA GeForce RTX 3090 Ti vs NVIDIA A100 SXM4 80 GB

Comparative analysis of NVIDIA GeForce RTX 3090 Ti and NVIDIA A100 SXM4 80 GB 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: PassMark - G2D Mark, PassMark - G3D Mark, Geekbench - OpenCL, 3DMark Fire Strike - Graphics Score, CompuBench 1.5 Desktop - Face Detection (mPixels/s), CompuBench 1.5 Desktop - T-Rex (Frames/s), CompuBench 1.5 Desktop - Video Composition (Frames/s), CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s).

 

Differences

Reasons to consider the NVIDIA GeForce RTX 3090 Ti

  • Videocard is newer: launch date 1 year(s) 2 month(s) later
  • Around 42% higher core clock speed: 1560 MHz vs 1095 MHz
  • Around 32% higher boost clock speed: 1860 MHz vs 1410 MHz
  • Around 3% higher texture fill rate: 625.0 GTexel/s vs 609.1 GTexel/s
  • Around 56% higher pipelines: 10752 vs 6912
Launch date 27 Jan 2022 vs 16 Nov 2020
Core clock speed 1560 MHz vs 1095 MHz
Boost clock speed 1860 MHz vs 1410 MHz
Texture fill rate 625.0 GTexel/s vs 609.1 GTexel/s
Pipelines 10752 vs 6912

Reasons to consider the NVIDIA A100 SXM4 80 GB

  • A newer manufacturing process allows for a more powerful, yet cooler running videocard: 7 nm vs 8 nm
  • Around 13% lower typical power consumption: 400 Watt vs 450 Watt
  • 3.3x more maximum memory size: 80 GB vs 24 GB
  • Around 21% higher memory clock speed: 1593 MHz (3.2 Gbps effective) vs 1313 MHz, 21 Gbps effective
  • Around 2% better performance in Geekbench - OpenCL: 209899 vs 205205
Specifications (specs)
Manufacturing process technology 7 nm vs 8 nm
Thermal Design Power (TDP) 400 Watt vs 450 Watt
Maximum memory size 80 GB vs 24 GB
Memory clock speed 1593 MHz (3.2 Gbps effective) vs 1313 MHz, 21 Gbps effective
Benchmarks
Geekbench - OpenCL 209899 vs 205205

Compare benchmarks

GPU 1: NVIDIA GeForce RTX 3090 Ti
GPU 2: NVIDIA A100 SXM4 80 GB

Geekbench - OpenCL
GPU 1
GPU 2
205205
209899
Name NVIDIA GeForce RTX 3090 Ti NVIDIA A100 SXM4 80 GB
PassMark - G2D Mark 1226
PassMark - G3D Mark 29671
Geekbench - OpenCL 205205 209899
3DMark Fire Strike - Graphics Score 22131
CompuBench 1.5 Desktop - Face Detection (mPixels/s) 259.78
CompuBench 1.5 Desktop - T-Rex (Frames/s) 63.049
CompuBench 1.5 Desktop - Video Composition (Frames/s) 177.665
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s) 3026.082

Compare specifications (specs)

NVIDIA GeForce RTX 3090 Ti NVIDIA A100 SXM4 80 GB

Essentials

Architecture Ampere Ampere
Code name GA102 GA100
Launch date 27 Jan 2022 16 Nov 2020
Place in performance rating 27 28

Technical info

Boost clock speed 1860 MHz 1410 MHz
Core clock speed 1560 MHz 1095 MHz
Manufacturing process technology 8 nm 7 nm
Peak Double Precision (FP64) Performance 625.0 GFLOPS (1:64) 9.746 TFLOPS (1:2)
Peak Half Precision (FP16) Performance 40.00 TFLOPS (1:1) 77.97 TFLOPS (4:1)
Peak Single Precision (FP32) Performance 40.00 TFLOPS 19.49 TFLOPS
Pipelines 10752 6912
Pixel fill rate 208.3 GPixel/s 225.6 GPixel/s
Texture fill rate 625.0 GTexel/s 609.1 GTexel/s
Thermal Design Power (TDP) 450 Watt 400 Watt
Transistor count 28300 million 54200 million

Video outputs and ports

Display Connectors 1x HDMI 2.1, 3x DisplayPort 1.4a No outputs

Compatibility, dimensions and requirements

Form factor Triple-slot IGP
Height 61 mm, 2.4 inches
Interface PCIe 4.0 x16 PCIe 4.0 x16
Length 336 mm, 13.2 inches
Recommended system power (PSU) 850 Watt 800 Watt
Supplementary power connectors 1x 16-pin None
Width 140 mm, 5.5 inches

API support

DirectX 12 Ultimate (12_2)
OpenCL 3.0 3.0
OpenGL 4.6
Shader Model 6.7
Vulkan

Memory

Maximum RAM amount 24 GB 80 GB
Memory bandwidth 1,008 GB/s 2039 GB/s
Memory bus width 384 bit 5120 bit
Memory clock speed 1313 MHz, 21 Gbps effective 1593 MHz (3.2 Gbps effective)
Memory type GDDR6X HBM2e
High bandwidth memory (HBM)