NVIDIA A40 vs NVIDIA A100 SXM4 40 GB

Comparative analysis of NVIDIA A40 and NVIDIA A100 SXM4 40 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: Geekbench - OpenCL, GFXBench 4.0 - Car Chase Offscreen (Frames), GFXBench 4.0 - Car Chase Offscreen (Fps), GFXBench 4.0 - Manhattan (Frames), GFXBench 4.0 - Manhattan (Fps), GFXBench 4.0 - T-Rex (Frames), GFXBench 4.0 - T-Rex (Fps).

 

Differences

Reasons to consider the NVIDIA A40

  • Videocard is newer: launch date 4 month(s) later
  • Around 19% higher core clock speed: 1305 MHz vs 1095 MHz
  • Around 23% higher boost clock speed: 1740 MHz vs 1410 MHz
  • Around 56% higher pipelines: 10752 vs 6912
  • Around 33% lower typical power consumption: 300 Watt vs 400 Watt
  • Around 20% higher maximum memory size: 48 GB vs 40 GB
  • Around 49% higher memory clock speed: 1812 MHz (14.5 Gbps effective) vs 1215 MHz (2.4 Gbps effective)
Launch date 5 Oct 2020 vs 14 May 2020
Core clock speed 1305 MHz vs 1095 MHz
Boost clock speed 1740 MHz vs 1410 MHz
Pipelines 10752 vs 6912
Thermal Design Power (TDP) 300 Watt vs 400 Watt
Maximum memory size 48 GB vs 40 GB
Memory clock speed 1812 MHz (14.5 Gbps effective) vs 1215 MHz (2.4 Gbps effective)

Reasons to consider the NVIDIA A100 SXM4 40 GB

  • Around 4% higher texture fill rate: 609.1 GTexel/s vs 584.6 GTexel/s
  • A newer manufacturing process allows for a more powerful, yet cooler running videocard: 7 nm vs 8 nm
  • Around 3% better performance in Geekbench - OpenCL: 190489 vs 185390
Specifications (specs)
Texture fill rate 609.1 GTexel/s vs 584.6 GTexel/s
Manufacturing process technology 7 nm vs 8 nm
Benchmarks
Geekbench - OpenCL 190489 vs 185390

Compare benchmarks

GPU 1: NVIDIA A40
GPU 2: NVIDIA A100 SXM4 40 GB

Geekbench - OpenCL
GPU 1
GPU 2
185390
190489
Name NVIDIA A40 NVIDIA A100 SXM4 40 GB
Geekbench - OpenCL 185390 190489
GFXBench 4.0 - Car Chase Offscreen (Frames) 21006
GFXBench 4.0 - Car Chase Offscreen (Fps) 21006
GFXBench 4.0 - Manhattan (Frames) 27823
GFXBench 4.0 - Manhattan (Fps) 27823
GFXBench 4.0 - T-Rex (Frames) 51880
GFXBench 4.0 - T-Rex (Fps) 51880

Compare specifications (specs)

NVIDIA A40 NVIDIA A100 SXM4 40 GB

Essentials

Architecture Ampere Ampere
Code name GA102 GA100
Launch date 5 Oct 2020 14 May 2020
Place in performance rating 5 3

Technical info

Boost clock speed 1740 MHz 1410 MHz
Core clock speed 1305 MHz 1095 MHz
Manufacturing process technology 8 nm 7 nm
Peak Double Precision (FP64) Performance 1169 GFLOPS (1:32) 9.746 TFLOPS (1:2)
Peak Half Precision (FP16) Performance 37.42 TFLOPS (1:1) 77.97 TFLOPS (4:1)
Peak Single Precision (FP32) Performance 37.42 TFLOPS 19.49 TFLOPS
Pipelines 10752 6912
Pixel fill rate 194.9 GPixel/s 225.6 GPixel/s
Texture fill rate 584.6 GTexel/s 609.1 GTexel/s
Thermal Design Power (TDP) 300 Watt 400 Watt
Transistor count 28300 million 54200 million

Video outputs and ports

Display Connectors 3x DisplayPort No outputs

Compatibility, dimensions and requirements

Form factor Dual-slot IGP
Interface PCIe 4.0 x16 PCIe 4.0 x16
Length 267 mm (10.5 inches)
Recommended system power (PSU) 700 Watt 800 Watt
Supplementary power connectors 8-pin EPS None
Width 112 mm (4.4 inches)

API support

DirectX 12.2
OpenCL 3.0 3.0
OpenGL 4.6
Shader Model 6.6
Vulkan

Memory

Maximum RAM amount 48 GB 40 GB
Memory bandwidth 695.8 GB/s 1555 GB/s
Memory bus width 384 bit 5120 bit
Memory clock speed 1812 MHz (14.5 Gbps effective) 1215 MHz (2.4 Gbps effective)
Memory type GDDR6 HBM2e
High bandwidth memory (HBM)