NVIDIA A40 PCIe vs AMD Radeon HD 8870 OEM
GPU · Specs Compare
Graphics Card
Release Date
Oct 2020
Jan 2013
Generation
Tesla
Sea Islands
Type
Desktop
Desktop
Bus Interface
PCIe 4.0 x16
PCIe 3.0 x16
Clock Speeds
Base Clock
1305 MHz
—
Boost Clock
1740 MHz
—
Memory Clock
1812 MHz
1200 MHz
Memory
Memory Size
48GB
2GB
Memory Type
GDDR6
GDDR5
Memory Bus
384bit
256bit
Bandwidth
695.8GB/s
153.6GB/s
Render Config
SM Count
84
—
Shading Units
10752
1280
TMUs
336
80
ROPs
112
32
Tensor Cores
336
—
RT Cores
84
—
L1 Cache
128 KB (per SM)
16 KB (per CU)
L2 Cache
6 MB
512 KB
Compute Units
—
20
Theoretical Performance
Pixel Rate
194.9 GPixel/s
32.00 GPixel/s
Texture Rate
584.6 GTexel/s
80.00 GTexel/s
FP16 (half)
37.42 TFLOPS
—
FP32 (float)
37.42 TFLOPS
2.560 TFLOPS
FP64 (double)
584.6 GFLOPS
160.0 GFLOPS
Graphics Processor
GPU Name
GA102
Pitcairn
Architecture
Ampere
GCN 1.0
Foundry
Samsung
TSMC
Process Size
8 nm
28 nm
Transistors
28.3 billion
2.8 billion
Die Size
628 mm²
212 mm²
GPU Variant
—
Pitcairn XT(215-0828047)
Board Design
TDP
300W
175W
Suggested PSU
700 W
450 W
Outputs
3x DisplayPort 1.4a
1x DVI1x HDMI 1.4a2x mini-DisplayPort 1.2
Power Connectors
8-pin EPS
2x 6-pin
Graphics Features
DirectX
12 Ultimate (12_2)
12 (11_1)
OpenGL
4.6
4.6
OpenCL
3.0
1.2
Vulkan
1.3
1.2
CUDA
8.6
—
Shader Model
6.6
5.1
▲ Specs Compare
Data sourced from official specifications and benchmark tests.