NVIDIA L40S vs AMD Radeon E9390 PCIe

GPU · Specs Compare

Products
GPU NVIDIA L40S NVIDIA · 2022-10
GPU AMD Radeon E9390 PCIe AMD · 2019-10
Graphics Card
Release Date
Oct 2022
Oct 2019
Generation
Server Ada
Embedded
Type
Professional
Mobile
Bus Interface
PCIe 4.0 x16
PCIe 3.0 x16
Clock Speeds
Base Clock
1065 MHz
713 MHz
Boost Clock
2520 MHz
1089 MHz
Memory Clock
2250 MHz
1250 MHz
Memory
Memory Size
48GB
8GB
Memory Type
GDDR6
GDDR5
Memory Bus
384bit
256bit
Bandwidth
864.0GB/s
160.0GB/s
Render Config
SM Count
142
—
Shading Units
18176
1792
TMUs
568
112
ROPs
192
32
Tensor Cores
568
—
RT Cores
142
—
L1 Cache
128 KB (per SM)
16 KB (per CU)
L2 Cache
48 MB
2 MB
Compute Units
—
28
Theoretical Performance
Pixel Rate
483.8 GPixel/s
34.85 GPixel/s
Texture Rate
1431.4 GTexel/s
122.0 GTexel/s
FP16 (half)
91.61 TFLOPS
3.903 TFLOPS
FP32 (float)
91.61 TFLOPS
3.903 TFLOPS
FP64 (double)
1431.4 GFLOPS
243.9 GFLOPS
Graphics Processor
GPU Name
AD102
Ellesmere
GPU Variant
AD102-896-A1
—
Architecture
Ada Lovelace
GCN 4.0
Foundry
TSMC
GlobalFoundries
Process Size
5 nm
14 nm
Transistors
76.3 billion
5.7 billion
Die Size
609 mm²
232 mm²
Board Design
TDP
350W
75W
Suggested PSU
750 W
—
Outputs
4x DisplayPort 1.4a
4x DisplayPort 1.4a
Power Connectors
1x 16-pin
None
Graphics Features
DirectX
12 Ultimate (12_2)
12 (12_0)
OpenGL
4.6
4.6
OpenCL
3.0
2.1
Vulkan
1.4
1.2
CUDA
8.9
—
Shader Model
6.9
6.4
Benchmark
Blender
9,239
—
▲ Specs Compare Data sourced from official specifications and benchmark tests.