GPU Comparison
GEFORCE
NVIDIA L20
CORE STATE
AD102
VRAM
48 GB
CLOCK SPEED
2520 MHz
TDP
275 W
BUS WIDTH
384 bit
ARCHITECTURE
Ada Lovelace
PROCESS
5 nm
LAUNCH DATE
2023
VS
GEFORCE
P104-100
CORE STATE
GP104
VRAM
4 GB
CLOCK SPEED
1733 MHz
TDP
—
BUS WIDTH
256 bit
ARCHITECTURE
Pascal
PROCESS
16 nm
LAUNCH DATE
2017
PERFORMANCE BENCHMARKS
geekbench_opencl
3dmark_3dmark_steel_nomad_dx12
geekbench_vulkan
DETAILED SPECIFICATIONS
SPECIFICATION
L20
P104-100
Core Specs
Shading Units
11,776
1,920
-83.7%
Shaders
11,776
1,920
-83.7%
TMUs
368
120
-67.4%
ROPs
128
64
-50.0%
SM Count
92
15
-83.7%
Clocks
Base Clock
1440 MHz
1607 MHz
Boost Clock
2520 MHz
1733 MHz
Memory Clock
2250 MHz
18 Gbps effective
1251 MHz
10 Gbps effective
Memory
Memory Size
48 GB
4 GB
VRAM (MB)
49,152
4,096
-91.7%
Memory Type
GDDR6
GDDR5X
Memory Bus
384 bit
256 bit
Bandwidth
864.0 GB/s
320.3 GB/s
Cache
L1 Cache
128 KB (per SM)
48 KB (per SM)
L2 Cache
96 MB
2 MB
Performance
Pixel Rate
322.6 GPixel/s
110.9 GPixel/s
Texture Rate
927.4 GTexel/s
208.0 GTexel/s
FP32 (TFLOPS)
59.35 TFLOPS
6.655 TFLOPS
FP64 (TFLOPS)
927.4 GFLOPS (1:64)
208.0 GFLOPS (1:32)
FP16 (TFLOPS)
59.35 TFLOPS (1:1)
104.0 GFLOPS (1:64)
AI/RT
RT Cores
92
—
Tensor Cores
368
—
Power
TDP
275 W
—
TDP (W)
275
—
Suggested PSU
600 W
200 W
Power Connectors
1x 16-pin
1x 8-pin
Architecture
Architecture
Ada Lovelace
Pascal
GPU Name
AD102
GP104
Generation
Server Ada
(Lxx)
Mining GPUs
Process Size
5 nm
16 nm
Transistors
76,300 million
7,200 million
Die Size
609 mm²
314 mm²
Foundry
TSMC
TSMC
Density
125.3M / mm²
22.9M / mm²
API Support
DirectX
12 Ultimate (12_2)
12 (12_1)
OpenGL
4.6
4.6
Vulkan
1.4
1.4
OpenCL
3.0
3.0
CUDA
8.9
6.1
Shader Model
6.8
6.8
Physical
Slot Width
Dual-slot
Dual-slot
Length
267 mm
10.5 inches
267 mm
10.5 inches
Height
111 mm
4.4 inches
—
Outputs
4x DisplayPort 1.4a
No outputs
Bus Interface
PCIe 4.0 x16
PCIe 1.0 x4
Other
Production
Active
End-of-life
Predecessor
Server Ampere
—
Successor
Server Hopper
—