NVIDIA A100 PCIe vs AMD Radeon HD 6870 1600SP Edition

GPU Specs Compare

Graphics Card

Release Date
Jun 2020
Jan 2013
Generation
Tesla
Northern Islands
Type
AI GPU
Desktop
Bus Interface
PCIe 4.0 x16
PCIe 2.0 x16

Clock Speeds

Base Clock
765 MHz
-
Boost Clock
1410 MHz
-
Memory Clock
1215 MHz
1050 MHz

Memory

Memory Size
40GB
1024MB
Memory Type
HBM2e
GDDR5
Memory Bus
5120bit
256bit
Bandwidth
1555GB/s
134.4GB/s

Render Config

SM Count
108
-
Shading Units
6912
1600
TMUs
432
80
ROPs
160
32
Tensor Cores
432
-
L1 Cache
192 KB (per SM)
8 KB (per CU)
L2 Cache
40 MB
512 KB
Compute Units
-
20

Theoretical Performance

Pixel Rate
225.6 GPixel/s
27.20 GPixel/s
Texture Rate
609.1 GTexel/s
68.00 GTexel/s
FP16 (half)
77.97 TFLOPS
-
FP32 (float)
19.49 TFLOPS
2.720 TFLOPS
FP64 (double)
9.746 TFLOPS
544.0 GFLOPS

Graphics Processor

GPU Name
GA100
Cypress
Architecture
Ampere
TeraScale 2
Foundry
TSMC
TSMC
Process Size
7 nm
40 nm
Transistors
54.2 billion
2.154 billion
Die Size
826 mm²
334 mm²
GPU Variant
-
Cypress XT(215-0735033)

Board Design

TDP
250W
175W
Suggested PSU
600 W
450 W
Outputs
No outputs
2x DVI1x HDMI 1.3a2x mini-DisplayPort 1.1
Power Connectors
8-pin EPS
2x 6-pin

Graphics Features

DirectX
N/A
11.2 (11_0)
OpenGL
N/A
4.4
OpenCL
3.0
1.2
Vulkan
N/A
N/A
CUDA
8.0
-
Shader Model
N/A
5.0