AMD Radeon PRO W7900 vs NVIDIA L40S

GPU Specs Compare

G

NVIDIA L40S

NVIDIA 2022-10

Graphics Card

Release Date
May 2023
Oct 2022
Generation
Radeon Pro Navi
Server Ada
Type
Professional
Professional
Bus Interface
PCIe 4.0 x16
PCIe 4.0 x16

Clock Speeds

Base Clock
1760 MHz
1065 MHz
Boost Clock
2495 MHz
2520 MHz
Memory Clock
2250 MHz
2250 MHz

Memory

Memory Size
48GB
48GB
Memory Type
GDDR6
GDDR6
Memory Bus
384bit
384bit
Bandwidth
864.0GB/s
864.0GB/s

Render Config

Compute Units
96
-
Shading Units
6144
18176
TMUs
384
568
ROPs
192
192
RT Cores
96
142
L1 Cache
256 KB per Array
128 KB (per SM)
L2 Cache
6 MB
48 MB
L3 Cache
96 MB
-
SM Count
-
142
Tensor Cores
-
568

Theoretical Performance

Pixel Rate
479.0 GPixel/s
483.8 GPixel/s
Texture Rate
958.1 GTexel/s
1431.4 GTexel/s
FP16 (half)
122.6 TFLOPS
91.61 TFLOPS
FP32 (float)
61.32 TFLOPS
91.61 TFLOPS
FP64 (double)
1.916 TFLOPS
1431.4 GFLOPS

Graphics Processor

GPU Name
Navi 31
AD102
GPU Variant
Navi 31 XTW
AD102-896-A1
Architecture
RDNA 3.0
Ada Lovelace
Foundry
TSMC
TSMC
Process Size
5 nm
5 nm
Transistors
57.7 billion
76.3 billion
Die Size
529 mm²
609 mm²

Board Design

TDP
295W
350W
Suggested PSU
600 W
750 W
Outputs
3x DisplayPort 2.11x mini-DisplayPort 2.1
4x DisplayPort 1.4a
Power Connectors
2x 8-pin
1x 16-pin

Graphics Features

DirectX
12 Ultimate (12_2)
12 Ultimate (12_2)
OpenGL
4.6
4.6
OpenCL
2.0
3.0
Vulkan
1.4
1.4
Shader Model
6.9
6.9
CUDA
-
8.9

📊 Benchmark

Blender
-
9,239