GPU Comparison
GEFORCE
NVIDIA CMP 90HX
CORE STATE
GA102
VRAM
10 GB
CLOCK SPEED
1710 MHz
TDP
320 W
BUS WIDTH
320 bit
ARCHITECTURE
Ampere
PROCESS
8 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
Analysis: NVIDIA CMP 90HX vs NVIDIA L40
Looking at the test figures for the NVIDIA L40 and GeForce NVIDIA CMP 90HX, a trend of competitive frame rates unfolds. Not one GPU leads reliably over most scenarios. The alternating of wins means core equality. Those face a genuine decision between them. Either cards offer competent rendering throughput.
When buyers conflicted between the NVIDIA L40 and GeForce NVIDIA CMP 90HX, remain certain that either selection provides equivalent gaming capability. The benchmark numbers supports zero definite leader. Base your determination on secondary variables and experience solid gaming throughput no matter what. Either are capable in their respective sense. Select confidently.
DETAILED SPECIFICATIONS
SPECIFICATION
CMP 90HX
L40
Core Specs
Shading Units
6,400
18,176
+184.0%
Shaders
6,400
18,176
+184.0%
TMUs
200
568
+184.0%
ROPs
80
192
+140.0%
SM Count
50
142
+184.0%
Clocks
Base Clock
1500 MHz
735 MHz
Boost Clock
1710 MHz
2490 MHz
Memory Clock
1188 MHz
19 Gbps effective
2250 MHz
18 Gbps effective
Memory
Memory Size
10 GB
48 GB
VRAM (MB)
10,240
49,152
+380.0%
Memory Type
GDDR6X
GDDR6
Memory Bus
320 bit
384 bit
Bandwidth
760.3 GB/s
864.0 GB/s
Cache
L1 Cache
128 KB (per SM)
128 KB (per SM)
L2 Cache
5 MB
96 MB
Performance
Pixel Rate
136.8 GPixel/s
478.1 GPixel/s
Texture Rate
342.0 GTexel/s
1,414.3 GTexel/s
FP32 (TFLOPS)
21.89 TFLOPS
90.52 TFLOPS
FP64 (TFLOPS)
342.0 GFLOPS (1:64)
1,414.3 GFLOPS (1:64)
FP16 (TFLOPS)
21.89 TFLOPS (1:1)
90.52 TFLOPS (1:1)
AI/RT
RT Cores
50
142
+184.0%
Tensor Cores
200
568
+184.0%
Power
TDP
320 W
300 W
TDP (W)
320
300
-6.3%
Suggested PSU
700 W
700 W
Power Connectors
2x 8-pin
1x 16-pin
Architecture
Architecture
Ampere
Ada Lovelace
GPU Name
GA102
AD102
Generation
Mining GPUs
Server Ada
(Lxx)
Process Size
8 nm
5 nm
Transistors
28,300 million
76,300 million
Die Size
628 mm²
609 mm²
Foundry
Samsung
TSMC
Density
45.1M / mm²
125.3M / mm²
API Support
DirectX
12 Ultimate (12_2)
12 Ultimate (12_2)
OpenGL
4.6
4.6
Vulkan
1.4
1.4
OpenCL
3.0
3.0
CUDA
8.6
8.9
Shader Model
6.8
6.8
Physical
Slot Width
Dual-slot
Dual-slot
Length
285 mm
11.2 inches
267 mm
10.5 inches
Height
112 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
Production
End-of-life
End-of-life
Predecessor
—
Server Ampere
Successor
—
Server Hopper