GPU Comparison
GEFORCE
NVIDIA CMP 30HX
CORE STATE
TU116
VRAM
6 GB
CLOCK SPEED
1785 MHz
TDP
125 W
BUS WIDTH
192 bit
ARCHITECTURE
Turing
PROCESS
12 nm
LAUNCH DATE
2021
VS
GEFORCE
L40
CORE STATE
AD102
VRAM
48 GB
CLOCK SPEED
2490 MHz
TDP
300 W
BUS WIDTH
384 bit
ARCHITECTURE
Ada Lovelace
PROCESS
5 nm
LAUNCH DATE
2022
PERFORMANCE BENCHMARKS
geekbench_opencl
geekbench_vulkan
DETAILED SPECIFICATIONS
SPECIFICATION
CMP 30HX
L40
Core Specs
Shading Units
1,408
18,176
+1190.9%
Shaders
1,408
18,176
+1190.9%
TMUs
88
568
+545.5%
ROPs
48
192
+300.0%
SM Count
22
142
+545.5%
Clocks
Base Clock
1530 MHz
735 MHz
Boost Clock
1785 MHz
2490 MHz
Memory Clock
1750 MHz
14 Gbps effective
2250 MHz
18 Gbps effective
Memory
Memory Size
6 GB
48 GB
VRAM (MB)
6,144
49,152
+700.0%
Memory Type
GDDR6
GDDR6
Memory Bus
192 bit
384 bit
Bandwidth
336.0 GB/s
864.0 GB/s
Cache
L1 Cache
64 KB (per SM)
128 KB (per SM)
L2 Cache
1536 KB
96 MB
Performance
Pixel Rate
85.68 GPixel/s
478.1 GPixel/s
Texture Rate
157.1 GTexel/s
1,414.3 GTexel/s
FP32 (TFLOPS)
5.027 TFLOPS
90.52 TFLOPS
FP64 (TFLOPS)
157.1 GFLOPS (1:32)
1,414.3 GFLOPS (1:64)
FP16 (TFLOPS)
10.05 TFLOPS (2:1)
90.52 TFLOPS (1:1)
AI/RT
RT Cores
—
142
Tensor Cores
—
568
Power
TDP
125 W
300 W
TDP (W)
125
300
+140.0%
Suggested PSU
300 W
700 W
Power Connectors
1x 8-pin
1x 16-pin
Architecture
Architecture
Turing
Ada Lovelace
GPU Name
TU116
AD102
Generation
Mining GPUs
Server Ada
(Lxx)
Process Size
12 nm
5 nm
Transistors
6,600 million
76,300 million
Die Size
284 mm²
609 mm²
Foundry
TSMC
TSMC
Density
23.2M / mm²
125.3M / mm²
API Support
DirectX
12 (12_1)
12 Ultimate (12_2)
OpenGL
4.6
4.6
Vulkan
1.4
1.4
OpenCL
3.0
3.0
CUDA
7.5
8.9
Shader Model
6.8
6.8
Physical
Slot Width
Dual-slot
Dual-slot
Length
229 mm
9 inches
267 mm
10.5 inches
Height
111 mm
4.4 inches
111 mm
4.4 inches
Outputs
No outputs
4x DisplayPort 1.4a
Bus Interface
PCIe 1.0 x4
PCIe 4.0 x16
Other
Launch Price
799 USD
—
Production
End-of-life
End-of-life
Predecessor
—
Server Ampere
Successor
—
Server Hopper